along/Mars-RAG-paper
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

修改创新点

Browse Source
This commit is contained in:
龙澳
2026-04-03 18:56:07 +08:00
parent da913b6ccc
commit 19255963d6
10 changed files with 237 additions and 189 deletions
Download Patch File Download Diff File Expand all files Collapse all files

56
MarsRAG/MarsRAG.aux
View File

@@ -10,59 +10,67 @@
\citation{Lewis20RAG} \citation{Lewis20RAG}
\citation{Zhou24hallucination} \citation{Zhou24hallucination}
\citation{Pan24KGandLLM} \citation{Pan24KGandLLM}
\citation{Wu25MultiRAG}
\citation{Wu25MultiRAG}
\@writefile{toc}{\contentsline {section}{\numberline {I}Introduction}{1}{}\protected@file@percent } \@writefile{toc}{\contentsline {section}{\numberline {I}Introduction}{1}{}\protected@file@percent }
\citation{Wu25MultiRAG} \citation{Wu25MultiRAG}
\@writefile{toc}{\contentsline {section}{\numberline {II}Preliminary}{3}{}\protected@file@percent } \citation{Wang25Astute}
\newlabel{equ:RAG Problem}{{1}{3}} \citation{placeholder_HyperRAG}
\citation{placeholder_HypRAG}
\citation{placeholder_TruthfulRAG}
\citation{placeholder_Diagnosing}
\@writefile{toc}{\contentsline {section}{\numberline {II}Preliminary}{2}{}\protected@file@percent }
\newlabel{equ:RAG Problem}{{1}{2}}
\newlabel{equ:RAG Problem s.t.}{{2}{3}} \newlabel{equ:RAG Problem s.t.}{{2}{3}}
\newlabel{equ:spatial observation hyperedge}{{3}{3}} \newlabel{equ:spatial observation hyperedge}{{3}{3}}
\newlabel{equ:hyperbolic space}{{4}{3}} \newlabel{equ:hyperbolic space}{{4}{3}}
\@writefile{toc}{\contentsline {section}{\numberline {III}Methodology}{4}{}\protected@file@percent } \@writefile{toc}{\contentsline {section}{\numberline {III}Methodology}{3}{}\protected@file@percent }
\@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {III-A}}Framework of AreoRAG}{4}{}\protected@file@percent } \@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {III-A}}Framework of AreoRAG}{3}{}\protected@file@percent }
\@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {III-B}}Hyperbolic Spatial Hypergraph Construction}{4}{}\protected@file@percent } \@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {III-B}}Hyperbolic Spatial Hypergraph Construction}{4}{}\protected@file@percent }
\newlabel{equ:multi-source spatial data}{{5}{4}} \newlabel{equ:multi-source spatial data}{{5}{4}}
\newlabel{equ:planetary science domain schema}{{6}{4}} \newlabel{equ:planetary science domain schema}{{6}{4}}
\newlabel{equ:embedding mapping}{{7}{5}} \newlabel{equ:embedding mapping}{{7}{4}}
\newlabel{equ:Spatial Scale-Curvature Correspondence}{{8}{5}} \newlabel{equ:Spatial Scale-Curvature Correspondence}{{8}{4}}
\newlabel{equ:Cross-Reference-Frame Alignment}{{9}{5}} \newlabel{equ:Cross-Reference-Frame Alignment}{{9}{4}}
\@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {III-C}}Spatiotemporal Retrieval with Cross-Resolution Aggregation}{5}{}\protected@file@percent } \@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {III-C}}Spatiotemporal Retrieval with Cross-Resolution Aggregation}{5}{}\protected@file@percent }
\newlabel{equ:Spatial Intent Extraction and Hyperedge Retrieval}{{10}{5}} \newlabel{equ:Spatial Intent Extraction and Hyperedge Retrieval}{{10}{5}}
\newlabel{equ:spatiotemporal encoding}{{11}{5}} \newlabel{equ:spatiotemporal encoding}{{11}{5}}
\newlabel{equ:hyperbolic spatial encoding}{{12}{5}} \newlabel{equ:hyperbolic spatial encoding}{{12}{5}}
\newlabel{equ:MLP scores}{{13}{5}} \newlabel{equ:MLP scores}{{13}{5}}
\@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {III-D}}Physics-Informed Conflict Triage}{6}{}\protected@file@percent } \@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {III-D}}Physics-Informed Conflict Triage}{5}{}\protected@file@percent }
\@writefile{lot}{\contentsline {table}{\numberline {I}{\ignorespaces Physics-Informed Conflict Triage Categories}}{6}{}\protected@file@percent } \@writefile{lot}{\contentsline {table}{\numberline {I}{\ignorespaces Physics-Informed Conflict Triage Categories}}{6}{}\protected@file@percent }
\newlabel{table_conflict_triage}{{I}{6}} \newlabel{table_conflict_triage}{{I}{6}}
\@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {III-E}}AreoRAG Prompting}{7}{}\protected@file@percent } \@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {III-E}}AreoRAG Prompting}{6}{}\protected@file@percent }
\@writefile{loa}{\contentsline {algorithm}{\numberline {1}{\ignorespaces AreoRAG Prompting (ARP)}}{7}{}\protected@file@percent } \@writefile{loa}{\contentsline {algorithm}{\numberline {1}{\ignorespaces AreoRAG Prompting (ARP)}}{7}{}\protected@file@percent }
\newlabel{alg:arp}{{1}{7}} \newlabel{alg:arp}{{1}{7}}
\@writefile{toc}{\contentsline {section}{\numberline {IV}Experiments}{8}{}\protected@file@percent } \@writefile{toc}{\contentsline {section}{\numberline {IV}Experiments}{7}{}\protected@file@percent }
\@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {IV-A}}Experimental Settings}{8}{}\protected@file@percent } \@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {IV-A}}Experimental Settings}{7}{}\protected@file@percent }
\@writefile{lot}{\contentsline {table}{\numberline {II}{\ignorespaces Statistics of the Planetary Datasets}}{8}{}\protected@file@percent } \@writefile{lot}{\contentsline {table}{\numberline {II}{\ignorespaces Statistics of the Planetary Datasets}}{8}{}\protected@file@percent }
\newlabel{table_planetary_datasets}{{II}{8}} \newlabel{table_planetary_datasets}{{II}{8}}
\@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {IV-B}}Overall Retrieval and QA Performance (Q1)}{9}{}\protected@file@percent } \@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {IV-B}}Overall Retrieval and QA Performance (Q1)}{8}{}\protected@file@percent }
\@writefile{lot}{\contentsline {table}{\numberline {III}{\ignorespaces Comparison with Baseline Methods on Planetary and General QA Datasets}}{9}{}\protected@file@percent }
\newlabel{table_comparison}{{III}{9}}
\@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {IV-C}}Robustness Under Spatial Sparsity and Conflict Intensity (Q2)}{9}{}\protected@file@percent } \@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {IV-C}}Robustness Under Spatial Sparsity and Conflict Intensity (Q2)}{9}{}\protected@file@percent }
\@writefile{lot}{\contentsline {table}{\numberline {III}{\ignorespaces Comparison with Baseline Methods on Planetary and General QA Datasets}}{10}{}\protected@file@percent } \@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {IV-D}}Ablation Study (Q3)}{9}{}\protected@file@percent }
\newlabel{table_comparison}{{III}{10}}
\@writefile{lot}{\contentsline {table}{\numberline {IV}{\ignorespaces Ablation Experiments of HySH and PICT Modules}}{10}{}\protected@file@percent } \@writefile{lot}{\contentsline {table}{\numberline {IV}{\ignorespaces Ablation Experiments of HySH and PICT Modules}}{10}{}\protected@file@percent }
\newlabel{table_ablation}{{IV}{10}} \newlabel{table_ablation}{{IV}{10}}
\@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {IV-D}}Ablation Study (Q3)}{10}{}\protected@file@percent } \@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {IV-E}}Conflict Preservation Evaluation (Q4)}{10}{}\protected@file@percent }
\@writefile{lot}{\contentsline {table}{\numberline {V}{\ignorespaces Conflict Handling Performance on MarsConflict-50}}{11}{}\protected@file@percent } \@writefile{lot}{\contentsline {table}{\numberline {V}{\ignorespaces Conflict Handling Performance on MarsConflict-50}}{10}{}\protected@file@percent }
\newlabel{table_conflict}{{V}{11}} \newlabel{table_conflict}{{V}{10}}
\@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {IV-E}}Conflict Preservation Evaluation (Q4)}{11}{}\protected@file@percent } \@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {IV-F}}Efficiency Analysis (Q5)}{10}{}\protected@file@percent }
\@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {IV-F}}Efficiency Analysis (Q5)}{11}{}\protected@file@percent }
\@writefile{lot}{\contentsline {table}{\numberline {VI}{\ignorespaces Time Cost Analysis Across Modules}}{11}{}\protected@file@percent } \@writefile{lot}{\contentsline {table}{\numberline {VI}{\ignorespaces Time Cost Analysis Across Modules}}{11}{}\protected@file@percent }
\newlabel{table_time_cost}{{VI}{11}} \newlabel{table_time_cost}{{VI}{11}}
\@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {IV-G}}Case Study}{11}{}\protected@file@percent } \@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {IV-G}}Case Study}{11}{}\protected@file@percent }
\@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {IV-H}}Limitations}{11}{}\protected@file@percent } \@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {IV-H}}Limitations}{11}{}\protected@file@percent }
\@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {IV-I}}Related Work}{12}{}\protected@file@percent } \@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {IV-I}}Related Work}{11}{}\protected@file@percent }
\@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {IV-J}}Graph-Structured Retrieval Augmented Generation}{12}{}\protected@file@percent } \@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {IV-J}}Graph-Structured Retrieval Augmented Generation}{11}{}\protected@file@percent }
\@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {IV-K}}Hyperbolic Representation Learning for Retrieval}{12}{}\protected@file@percent } \@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {IV-K}}Hyperbolic Representation Learning for Retrieval}{12}{}\protected@file@percent }
\@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {IV-L}}Knowledge Conflict Detection and Resolution in RAG}{13}{}\protected@file@percent } \@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {IV-L}}Knowledge Conflict Detection and Resolution in RAG}{12}{}\protected@file@percent }
\@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {IV-M}}Intelligent Retrieval for Planetary Remote Sensing Data}{13}{}\protected@file@percent }
\bibstyle{IEEEtran} \bibstyle{IEEEtran}
\bibdata{IEEEabrv,references} \bibdata{IEEEabrv,references}
\bibcite{McEwen24HiRISE}{1} \bibcite{McEwen24HiRISE}{1}
\@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {IV-M}}Intelligent Retrieval for Planetary Remote Sensing Data}{13}{}\protected@file@percent }
\@writefile{toc}{\contentsline {section}{\numberline {V}Conclusion}{13}{}\protected@file@percent }
\bibcite{Malin07CTX}{2} \bibcite{Malin07CTX}{2}
\bibcite{Murchie07CRISM}{3} \bibcite{Murchie07CRISM}{3}
\bibcite{Smith01MOLA}{4} \bibcite{Smith01MOLA}{4}
@@ -74,6 +82,6 @@
\bibcite{Zhou24hallucination}{10} \bibcite{Zhou24hallucination}{10}
\bibcite{Pan24KGandLLM}{11} \bibcite{Pan24KGandLLM}{11}
\bibcite{Wu25MultiRAG}{12} \bibcite{Wu25MultiRAG}{12}
\@writefile{toc}{\contentsline {section}{\numberline {V}Conclusion}{14}{}\protected@file@percent } \bibcite{Wang25Astute}{13}
\@writefile{toc}{\contentsline {section}{References}{14}{}\protected@file@percent } \@writefile{toc}{\contentsline {section}{References}{14}{}\protected@file@percent }
\gdef \@abspage@last{14} \gdef \@abspage@last{14}

9
MarsRAG/MarsRAG.bbl
View File

@@ -111,4 +111,13 @@ W.~Wu, H.~Wang, B.~Li, P.~Huang, X.~Zhao, and L.~Liang, ``Multirag: A
retrieval augmented generation,'' in \emph{2025 IEEE 41st International retrieval augmented generation,'' in \emph{2025 IEEE 41st International
Conference on Data Engineering (ICDE)}, 2025, pp. 3070--3083. Conference on Data Engineering (ICDE)}, 2025, pp. 3070--3083.
\bibitem{Wang25Astute}
F.~Wang, X.~Wan, R.~Sun, J.~Chen, and S.~O. Arik, ``Astute {RAG}: Overcoming
imperfect retrieval augmentation and knowledge conflicts for large language
models,'' in \emph{Proceedings of the 63rd Annual Meeting of the Association
for Computational Linguistics (Volume 1: Long Papers)}, W.~Che, J.~Nabende,
E.~Shutova, and M.~T. Pilehvar, Eds.\hskip 1em plus 0.5em minus 0.4em\relax
Vienna, Austria: Association for Computational Linguistics, Jul. 2025, pp.
30\,553--30\,571.
\end{thebibliography} \end{thebibliography}

64
MarsRAG/MarsRAG.blg
View File

@@ -17,44 +17,44 @@ Database file #2: references.bib
-- See the "IEEEtran_bst_HOWTO.pdf" manual for usage information. -- See the "IEEEtran_bst_HOWTO.pdf" manual for usage information.
Done. Done.
You've used 12 entries, You've used 13 entries,
4087 wiz_defined-function locations, 4087 wiz_defined-function locations,
1697 strings with 28523 characters, 1706 strings with 28996 characters,
and the built_in function-call counts, 14692 in all, are: and the built_in function-call counts, 16123 in all, are:
= -- 937 = -- 1038
> -- 870 > -- 920
< -- 57 < -- 70
+ -- 445 + -- 476
- -- 212 - -- 227
* -- 777 * -- 856
:= -- 1868 := -- 2045
add.period$ -- 26 add.period$ -- 29
call.type$ -- 12 call.type$ -- 13
change.case$ -- 12 change.case$ -- 15
chr.to.int$ -- 102 chr.to.int$ -- 138
cite$ -- 12 cite$ -- 13
duplicate$ -- 1032 duplicate$ -- 1124
empty$ -- 1037 empty$ -- 1150
format.name$ -- 218 format.name$ -- 229
if$ -- 3442 if$ -- 3776
int.to.chr$ -- 0 int.to.chr$ -- 0
int.to.str$ -- 12 int.to.str$ -- 13
missing$ -- 287 missing$ -- 305
newline$ -- 59 newline$ -- 62
num.names$ -- 12 num.names$ -- 15
pop$ -- 762 pop$ -- 810
preamble$ -- 1 preamble$ -- 1
purify$ -- 0 purify$ -- 0
quote$ -- 2 quote$ -- 2
skip$ -- 1054 skip$ -- 1146
stack$ -- 0 stack$ -- 0
substring$ -- 325 substring$ -- 426
swap$ -- 893 swap$ -- 979
text.length$ -- 23 text.length$ -- 24
text.prefix$ -- 0 text.prefix$ -- 0
top$ -- 5 top$ -- 5
type$ -- 12 type$ -- 13
warning$ -- 0 warning$ -- 0
while$ -- 29 while$ -- 35
width$ -- 14 width$ -- 15
write$ -- 143 write$ -- 153

234
MarsRAG/MarsRAG.log
View File

@@ -1,4 +1,4 @@
This is pdfTeX, Version 3.141592653-2.6-1.40.25 (MiKTeX 23.4) (preloaded format=pdflatex 2025.10.23) 2 APR 2026 20:14 This is pdfTeX, Version 3.141592653-2.6-1.40.25 (MiKTeX 23.4) (preloaded format=pdflatex 2025.10.23) 3 APR 2026 17:37
entering extended mode entering extended mode
restricted \write18 enabled. restricted \write18 enabled.
%&-line parsing enabled. %&-line parsing enabled.
@@ -397,8 +397,8 @@ LaTeX Font Info: Trying to load font information for U+msb on input line 42.
(D:\software\ctex\MiKTeX\tex/latex/amsfonts\umsb.fd (D:\software\ctex\MiKTeX\tex/latex/amsfonts\umsb.fd
File: umsb.fd 2013/01/14 v3.01 AMS symbols B File: umsb.fd 2013/01/14 v3.01 AMS symbols B
) )
LaTeX Font Info: Trying to load font information for TS1+ptm on input line 5 LaTeX Font Info: Trying to load font information for TS1+ptm on input line 6
8. 2.
(D:\software\ctex\MiKTeX\tex/latex/psnfss\ts1ptm.fd (D:\software\ctex\MiKTeX\tex/latex/psnfss\ts1ptm.fd
File: ts1ptm.fd 2001/06/04 font definitions for TS1/ptm. File: ts1ptm.fd 2001/06/04 font definitions for TS1/ptm.
@@ -406,303 +406,333 @@ File: ts1ptm.fd 2001/06/04 font definitions for TS1/ptm.
d}}{D:/software/ctex/MiKTeX/fonts/enc/dvips/base/8r.enc} d}}{D:/software/ctex/MiKTeX/fonts/enc/dvips/base/8r.enc}
] [2] ]
Underfull \hbox (badness 1642) in paragraph at lines 82--83 Underfull \hbox (badness 2368) in paragraph at lines 63--64
\OT1/ptm/m/n/10 (Anti-Over-Smoothing Guar-an-tee) while main-tain-ing []\OT1/ptm/b/n/10 The Con-flict Over-Smoothing Prob-lem. \OT1/ptm/m/n/10 Ex-ist
-ing
[] []
[3]
Overfull \hbox (12.1057pt too wide) detected at line 157 LaTeX Warning: Citation `placeholder_HyperRAG' on page 2 undefined on input lin
e 71.
LaTeX Warning: Citation `placeholder_HypRAG' on page 2 undefined on input line
71.
LaTeX Warning: Citation `placeholder_TruthfulRAG' on page 2 undefined on input
line 73.
LaTeX Warning: Citation `placeholder_Diagnosing' on page 2 undefined on input l
ine 73.
Underfull \hbox (badness 2326) in paragraph at lines 73--74
\OT1/ptm/m/n/10 entropy-based con-flict de-tec-tion from [\OT1/ptm/b/n/10 ?\OT1
/ptm/m/n/10 ] and the
[]
Underfull \hbox (badness 1728) in paragraph at lines 73--74
\OT1/ptm/m/n/10 [\OT1/ptm/b/n/10 ?\OT1/ptm/m/n/10 ]. PICT clas-si-fies each int
er-source con-flict into
[]
[2] [3]
Overfull \hbox (12.1057pt too wide) detected at line 148
[][] [] \OML/cmm/m/it/10 : [][] [] \OML/cmm/m/it/10 :
[] []
[4]
Underfull \hbox (badness 1910) in paragraph at lines 171--172 Underfull \hbox (badness 1910) in paragraph at lines 162--163
[]\OT1/ptm/m/n/10 **Proposition 1** (Spa-tial Scale-Curvature Cor-re-spon- []\OT1/ptm/m/n/10 **Proposition 1** (Spa-tial Scale-Curvature Cor-re-spon-
[] []
[4]
Overfull \hbox (9.20645pt too wide) detected at line 211 Overfull \hbox (9.20645pt too wide) detected at line 202
[]\OT1/cmr/bx/n/10 x \OT1/cmr/m/n/10 = [] \OML/cmm/m/it/10 ; []\OT1/cmr/bx/n/10 x \OT1/cmr/m/n/10 = [] \OML/cmm/m/it/10 ;
[] []
Overfull \hbox (2.51953pt too wide) detected at line 216 Overfull \hbox (2.51953pt too wide) detected at line 207
[]\OML/cmm/m/it/10 []\OT1/cmr/m/n/10 (\OML/cmm/m/it/10 e[]; e[]\OT1/cmr/m/n/10 []\OML/cmm/m/it/10 []\OT1/cmr/m/n/10 (\OML/cmm/m/it/10 e[]; e[]\OT1/cmr/m/n/10
) = [] \OML/cmm/m/it/10 ; ) = [] \OML/cmm/m/it/10 ;
[] []
Underfull \hbox (badness 10000) in paragraph at lines 227--228 Underfull \hbox (badness 10000) in paragraph at lines 218--219
[]\OT1/ptm/m/n/10 Given spa-tial ob-ser-va-tion hy-per-edge em-bed-dings []\OT1/ptm/m/n/10 Given spa-tial ob-ser-va-tion hy-per-edge em-bed-dings
[] []
Underfull \hbox (badness 3895) in paragraph at lines 227--228 Underfull \hbox (badness 3895) in paragraph at lines 218--219
\OMS/cmsy/m/n/10 f\OT1/cmr/m/n/10 ^^H(\OML/cmm/m/it/10 f[]\OT1/cmr/m/n/10 )\OMS \OMS/cmsy/m/n/10 f\OT1/cmr/m/n/10 ^^H(\OML/cmm/m/it/10 f[]\OT1/cmr/m/n/10 )\OMS
/cmsy/m/n/10 g[] ^^Z \U/msb/m/n/10 H[]$ \OT1/ptm/m/n/10 with query-relevance we /cmsy/m/n/10 g[] ^^Z \U/msb/m/n/10 H[]$ \OT1/ptm/m/n/10 with query-relevance we
ights $\OML/cmm/m/it/10 w[]$ ights $\OML/cmm/m/it/10 w[]$
[] []
[5]
Overfull \hbox (113.53706pt too wide) detected at line 249 Overfull \hbox (113.53706pt too wide) detected at line 240
\OMS/cmsy/m/n/10 H[]\OT1/cmr/m/n/10 (\OML/cmm/m/it/10 p[]; p[] \OMS/cmsy/m/n/10 \OMS/cmsy/m/n/10 H[]\OT1/cmr/m/n/10 (\OML/cmm/m/it/10 p[]; p[] \OMS/cmsy/m/n/10
j \OML/cmm/m/it/10 q\OT1/cmr/m/n/10 ) = \OML/cmm/m/it/10 H [] \OMS/cmsy/m/n/10 j \OML/cmm/m/it/10 q\OT1/cmr/m/n/10 ) = \OML/cmm/m/it/10 H [] \OMS/cmsy/m/n/10
^^@ [] [] \OML/cmm/m/it/10 ; ^^@ [] [] \OML/cmm/m/it/10 ;
[] []
[5]
Overfull \hbox (41.67476pt too wide) in paragraph at lines 276--290 Overfull \hbox (41.67476pt too wide) in paragraph at lines 267--281
[][] [][]
[] []
Overfull \hbox (49.71666pt too wide) detected at line 294 Overfull \hbox (49.71666pt too wide) detected at line 285
\OT1/cmr/bx/n/10 z[] \OT1/cmr/m/n/10 = [] \OT1/cmr/bx/n/10 z[] \OT1/cmr/m/n/10 = []
[] []
[6]
Underfull \hbox (badness 3019) in paragraph at lines 302--303 Underfull \hbox (badness 3019) in paragraph at lines 293--294
[]\OT1/ptm/m/n/10 **Proposition 2** (Con-flict Type Sep-a-ra-bil-ity). *The []\OT1/ptm/m/n/10 **Proposition 2** (Con-flict Type Sep-a-ra-bil-ity). *The
[] []
Overfull \hbox (10.51593pt too wide) detected at line 306 Overfull \hbox (10.51593pt too wide) detected at line 297
\OML/cmm/m/it/10 C[]\OT1/cmr/m/n/10 (\OML/cmm/m/it/10 v\OT1/cmr/m/n/10 ) = [] \OML/cmm/m/it/10 C[]\OT1/cmr/m/n/10 (\OML/cmm/m/it/10 v\OT1/cmr/m/n/10 ) = []
[] []
LaTeX Font Info: Trying to load font information for OMS+ptm on input line 3 LaTeX Font Info: Trying to load font information for OMS+ptm on input line 3
29. 20.
(D:\software\ctex\MiKTeX\tex/latex/psnfss\omsptm.fd (D:\software\ctex\MiKTeX\tex/latex/psnfss\omsptm.fd
File: omsptm.fd File: omsptm.fd
) )
LaTeX Font Info: Font shape `OMS/ptm/m/n' in size <10> not available LaTeX Font Info: Font shape `OMS/ptm/m/n' in size <10> not available
(Font) Font shape `OMS/cmsy/m/n' tried instead on input line 329. (Font) Font shape `OMS/cmsy/m/n' tried instead on input line 320.
[7] [6]
Underfull \hbox (badness 10000) in paragraph at lines 383--383 Underfull \hbox (badness 10000) in paragraph at lines 374--374
|[] |[]
[] []
Overfull \hbox (14.39503pt too wide) in paragraph at lines 383--383 Overfull \hbox (14.39503pt too wide) in paragraph at lines 374--374
[] []
[] []
Underfull \hbox (badness 10000) in paragraph at lines 383--383 Underfull \hbox (badness 10000) in paragraph at lines 374--374
|[] |[]
[] []
Overfull \hbox (11.8429pt too wide) in paragraph at lines 383--383 Overfull \hbox (11.8429pt too wide) in paragraph at lines 374--374
[] []
[] []
Overfull \hbox (25.19485pt too wide) in paragraph at lines 386--386 Overfull \hbox (25.19485pt too wide) in paragraph at lines 377--377
[]|[]| []|[]|
[] []
Underfull \hbox (badness 10000) in paragraph at lines 386--386 Underfull \hbox (badness 10000) in paragraph at lines 377--377
|[] |[]
[] []
Overfull \hbox (27.67467pt too wide) in paragraph at lines 386--386 Overfull \hbox (27.67467pt too wide) in paragraph at lines 377--377
[] []
[] []
Underfull \hbox (badness 10000) in paragraph at lines 388--388 Underfull \hbox (badness 10000) in paragraph at lines 379--379
|[] |[]
[] []
Overfull \hbox (18.33882pt too wide) in paragraph at lines 388--388 Overfull \hbox (18.33882pt too wide) in paragraph at lines 379--379
[] []
[] []
Underfull \hbox (badness 10000) in paragraph at lines 390--390 Underfull \hbox (badness 10000) in paragraph at lines 381--381
|[] |[]
[] []
Overfull \hbox (27.23465pt too wide) in paragraph at lines 390--390 Overfull \hbox (27.23465pt too wide) in paragraph at lines 381--381
[] []
[] []
Underfull \hbox (badness 10000) in paragraph at lines 392--392 Underfull \hbox (badness 10000) in paragraph at lines 383--383
|[] |[]
[] []
Overfull \hbox (25.89078pt too wide) in paragraph at lines 392--392 Overfull \hbox (25.89078pt too wide) in paragraph at lines 383--383
[] []
[] []
Underfull \hbox (badness 10000) in paragraph at lines 394--394 Underfull \hbox (badness 10000) in paragraph at lines 385--385
|[] |[]
[] []
Overfull \hbox (14.54706pt too wide) in paragraph at lines 394--394 Overfull \hbox (14.54706pt too wide) in paragraph at lines 385--385
[] []
[] []
Underfull \hbox (badness 10000) in paragraph at lines 396--396 Underfull \hbox (badness 10000) in paragraph at lines 387--387
|[] |[]
[] []
Overfull \hbox (24.43471pt too wide) in paragraph at lines 396--396 Overfull \hbox (24.43471pt too wide) in paragraph at lines 387--387
[] []
[] []
Underfull \hbox (badness 10000) in paragraph at lines 396--396 Underfull \hbox (badness 10000) in paragraph at lines 387--387
|[] |[]
[] []
Overfull \hbox (30.10707pt too wide) in paragraph at lines 396--396 Overfull \hbox (30.10707pt too wide) in paragraph at lines 387--387
[] []
[] []
Underfull \hbox (badness 10000) in paragraph at lines 398--398 Underfull \hbox (badness 10000) in paragraph at lines 389--389
|[] |[]
[] []
Overfull \hbox (32.7467pt too wide) in paragraph at lines 398--398 Overfull \hbox (32.7467pt too wide) in paragraph at lines 389--389
[] []
[] []
Underfull \hbox (badness 10000) in paragraph at lines 398--398 Underfull \hbox (badness 10000) in paragraph at lines 389--389
|[] |[]
[] []
Overfull \hbox (30.10707pt too wide) in paragraph at lines 398--398 Overfull \hbox (30.10707pt too wide) in paragraph at lines 389--389
[] []
[] []
Underfull \hbox (badness 2452) in paragraph at lines 403--404 Underfull \hbox (badness 2452) in paragraph at lines 394--395
[]\OT1/ptm/m/n/10 Additionally, to val-i-date gen-er-al-iza-tion on es-tab-lish []\OT1/ptm/m/n/10 Additionally, to val-i-date gen-er-al-iza-tion on es-tab-lish
ed ed
[] []
[8] [7]
Underfull \hbox (badness 10000) in paragraph at lines 433--434 Underfull \hbox (badness 10000) in paragraph at lines 424--425
[]\OT1/ptm/m/n/10 1) **Stan-dard RAG** [6]: Con-ven-tional retrieval- []\OT1/ptm/m/n/10 1) **Stan-dard RAG** [6]: Con-ven-tional retrieval-
[] []
Underfull \hbox (badness 1603) in paragraph at lines 443--444 Underfull \hbox (badness 1603) in paragraph at lines 434--435
[]\OT1/ptm/m/n/10 5) **Hy-per-GraphRAG** [25]: Hypergraph-based RAG []\OT1/ptm/m/n/10 5) **Hy-per-GraphRAG** [25]: Hypergraph-based RAG
[] []
[8]
Underfull \hbox (badness 2698) in paragraph at lines 497--498 Underfull \hbox (badness 2698) in paragraph at lines 488--489
\OT1/ptm/m/n/10 ti-HopQA), Are-oRAG main-tains com-pet-i-tive per-for-mance \OT1/ptm/m/n/10 ti-HopQA), Are-oRAG main-tains com-pet-i-tive per-for-mance
[] []
[9]
Underfull \hbox (badness 10000) in paragraph at lines 542--542 Underfull \hbox (badness 10000) in paragraph at lines 533--533
[]|\OT1/ptm/m/n/8 w/o In-ter-ac-tion En-tropy (use []|\OT1/ptm/m/n/8 w/o In-ter-ac-tion En-tropy (use
[] []
Underfull \hbox (badness 3271) in paragraph at lines 549--550 Underfull \hbox (badness 3271) in paragraph at lines 540--541
[]\OT1/ptm/m/n/10 **a) HySH Mod-ule Anal-y-sis:** The HySH mod-ule []\OT1/ptm/m/n/10 **a) HySH Mod-ule Anal-y-sis:** The HySH mod-ule
[] []
Underfull \hbox (badness 1917) in paragraph at lines 551--552 Underfull \hbox (badness 1917) in paragraph at lines 542--543
\OT1/ptm/m/n/10 F1 im-prove-ment over Eu-clidean hy-per-graph (49.2% vs. \OT1/ptm/m/n/10 F1 im-prove-ment over Eu-clidean hy-per-graph (49.2% vs.
[] []
[9]
Underfull \vbox (badness 10000) has occurred while \output is active [] Underfull \hbox (badness 10000) in paragraph at lines 565--565
[10]
Underfull \hbox (badness 10000) in paragraph at lines 574--574
[]|\OT1/ptm/m/n/8 Standard []|\OT1/ptm/m/n/8 Standard
[] []
Underfull \hbox (badness 10000) in paragraph at lines 576--576 Underfull \hbox (badness 10000) in paragraph at lines 567--567
[]|\OT1/ptm/m/n/8 MultiRAG []|\OT1/ptm/m/n/8 MultiRAG
[] []
Underfull \hbox (badness 10000) in paragraph at lines 582--582 Underfull \hbox (badness 10000) in paragraph at lines 573--573
[]|\OT1/ptm/b/n/8 AreoRAG []|\OT1/ptm/b/n/8 AreoRAG
[] []
[11] [10] [11]
Package textcomp Info: Symbol \textrightarrow not provided by Package textcomp Info: Symbol \textrightarrow not provided by
(textcomp) font family ptm in TS1 encoding. (textcomp) font family ptm in TS1 encoding.
(textcomp) Default family used instead on input line 674. (textcomp) Default family used instead on input line 665.
Package textcomp Info: Symbol \textrightarrow not provided by Package textcomp Info: Symbol \textrightarrow not provided by
(textcomp) font family ptm in TS1 encoding. (textcomp) font family ptm in TS1 encoding.
(textcomp) Default family used instead on input line 674. (textcomp) Default family used instead on input line 665.
[12{D:/software/ctex/MiKTeX/fonts/enc/dvips/cm-super/cm-super-ts1.enc}] [12{D:/software/ctex/MiKTeX/fonts/enc/dvips/cm-super/cm-super-ts1.enc}]
[13] Underfull \hbox (badness 2495) in paragraph at lines 699--700
Underfull \hbox (badness 2495) in paragraph at lines 708--709
[]\OT1/ptm/m/n/10 This work is sup-ported by the Na-tional Key R&D []\OT1/ptm/m/n/10 This work is sup-ported by the Na-tional Key R&D
[] []
Underfull \hbox (badness 2799) in paragraph at lines 708--709 Underfull \hbox (badness 2799) in paragraph at lines 699--700
\OT1/ptm/m/n/10 Pro-gram of China ``In-ter-gov-ern-men-tal In-ter-na-tional Sci \OT1/ptm/m/n/10 Pro-gram of China ``In-ter-gov-ern-men-tal In-ter-na-tional Sci
- -
[] []
Underfull \hbox (badness 7576) in paragraph at lines 708--709 Underfull \hbox (badness 7576) in paragraph at lines 699--700
\OT1/ptm/m/n/10 ence and Tech-nol-ogy In-no-va-tion Co-op-er-a-tion" (Grant \OT1/ptm/m/n/10 ence and Tech-nol-ogy In-no-va-tion Co-op-er-a-tion" (Grant
[] []
(MarsRAG.bbl) [14] (MarsRAG.aux) ) (MarsRAG.bbl [13]) [14
] (MarsRAG.aux)
LaTeX Warning: There were undefined references.
)
Here is how much of TeX's memory you used: Here is how much of TeX's memory you used:
5477 strings out of 476331 5482 strings out of 476331
91312 string characters out of 5797649 91417 string characters out of 5797649
1895660 words of memory out of 5000000 1896660 words of memory out of 5000000
25824 multiletter control sequences out of 15000+600000 25829 multiletter control sequences out of 15000+600000
562405 words of font info for 135 fonts, out of 8000000 for 9000 562405 words of font info for 135 fonts, out of 8000000 for 9000
1145 hyphenation exceptions out of 8191 1145 hyphenation exceptions out of 8191
57i,19n,63p,2271b,410s stack positions out of 10000i,1000n,20000p,200000b,200000s 57i,19n,63p,2271b,408s stack positions out of 10000i,1000n,20000p,200000b,200000s
<D:/software/ctex/MiKTeX/fonts/type1/public/a <D:/software/ctex/MiKTeX/fonts/type1/public/amsfonts/cm/cmbx10.pfb><D:/softwa
msfonts/cm/cmbx10.pfb><D:/software/ctex/MiKTeX/fonts/type1/public/amsfonts/cm/c re/ctex/MiKTeX/fonts/type1/public/amsfonts/cm/cmbx7.pfb><D:/software/ctex/MiKTe
mbx7.pfb><D:/software/ctex/MiKTeX/fonts/type1/public/amsfonts/cm/cmex10.pfb><D: X/fonts/type1/public/amsfonts/cm/cmex10.pfb><D:/software/ctex/MiKTeX/fonts/type
/software/ctex/MiKTeX/fonts/type1/public/amsfonts/cm/cmmi10.pfb><D:/software/ct 1/public/amsfonts/cm/cmmi10.pfb><D:/software/ctex/MiKTeX/fonts/type1/public/ams
ex/MiKTeX/fonts/type1/public/amsfonts/cm/cmmi5.pfb><D:/software/ctex/MiKTeX/fon fonts/cm/cmmi5.pfb><D:/software/ctex/MiKTeX/fonts/type1/public/amsfonts/cm/cmmi
ts/type1/public/amsfonts/cm/cmmi6.pfb><D:/software/ctex/MiKTeX/fonts/type1/publ 6.pfb><D:/software/ctex/MiKTeX/fonts/type1/public/amsfonts/cm/cmmi7.pfb><D:/sof
ic/amsfonts/cm/cmmi7.pfb><D:/software/ctex/MiKTeX/fonts/type1/public/amsfonts/c tware/ctex/MiKTeX/fonts/type1/public/amsfonts/cm/cmmi8.pfb><D:/software/ctex/Mi
m/cmmi8.pfb><D:/software/ctex/MiKTeX/fonts/type1/public/amsfonts/cm/cmmi9.pfb>< KTeX/fonts/type1/public/amsfonts/cm/cmmi9.pfb><D:/software/ctex/MiKTeX/fonts/ty
D:/software/ctex/MiKTeX/fonts/type1/public/amsfonts/cm/cmr10.pfb><D:/software/c pe1/public/amsfonts/cm/cmr10.pfb><D:/software/ctex/MiKTeX/fonts/type1/public/am
tex/MiKTeX/fonts/type1/public/amsfonts/cm/cmr6.pfb><D:/software/ctex/MiKTeX/fon sfonts/cm/cmr6.pfb><D:/software/ctex/MiKTeX/fonts/type1/public/amsfonts/cm/cmr7
ts/type1/public/amsfonts/cm/cmr7.pfb><D:/software/ctex/MiKTeX/fonts/type1/publi .pfb><D:/software/ctex/MiKTeX/fonts/type1/public/amsfonts/cm/cmr8.pfb><D:/softw
c/amsfonts/cm/cmr8.pfb><D:/software/ctex/MiKTeX/fonts/type1/public/amsfonts/cm/ are/ctex/MiKTeX/fonts/type1/public/amsfonts/cm/cmr9.pfb><D:/software/ctex/MiKTe
cmr9.pfb><D:/software/ctex/MiKTeX/fonts/type1/public/amsfonts/cm/cmsy10.pfb><D: X/fonts/type1/public/amsfonts/cm/cmsy10.pfb><D:/software/ctex/MiKTeX/fonts/type
/software/ctex/MiKTeX/fonts/type1/public/amsfonts/cm/cmsy5.pfb><D:/software/cte 1/public/amsfonts/cm/cmsy5.pfb><D:/software/ctex/MiKTeX/fonts/type1/public/amsf
x/MiKTeX/fonts/type1/public/amsfonts/cm/cmsy7.pfb><D:/software/ctex/MiKTeX/font onts/cm/cmsy7.pfb><D:/software/ctex/MiKTeX/fonts/type1/public/amsfonts/cm/cmsy8
s/type1/public/amsfonts/cm/cmsy8.pfb><D:/software/ctex/MiKTeX/fonts/type1/publi .pfb><D:/software/ctex/MiKTeX/fonts/type1/public/amsfonts/symbols/msam10.pfb><D
c/amsfonts/symbols/msam10.pfb><D:/software/ctex/MiKTeX/fonts/type1/public/amsfo :/software/ctex/MiKTeX/fonts/type1/public/amsfonts/symbols/msbm10.pfb><D:/softw
nts/symbols/msbm10.pfb><D:/software/ctex/MiKTeX/fonts/type1/public/cm-super/sfr are/ctex/MiKTeX/fonts/type1/public/cm-super/sfrm1000.pfb><D:/software/ctex/MiKT
m1000.pfb><D:/software/ctex/MiKTeX/fonts/type1/urw/times/utmb8a.pfb><D:/softwar eX/fonts/type1/urw/times/utmb8a.pfb><D:/software/ctex/MiKTeX/fonts/type1/urw/ti
e/ctex/MiKTeX/fonts/type1/urw/times/utmbi8a.pfb><D:/software/ctex/MiKTeX/fonts/ mes/utmbi8a.pfb><D:/software/ctex/MiKTeX/fonts/type1/urw/times/utmr8a.pfb><D:/s
type1/urw/times/utmr8a.pfb><D:/software/ctex/MiKTeX/fonts/type1/urw/times/utmri oftware/ctex/MiKTeX/fonts/type1/urw/times/utmri8a.pfb>
8a.pfb> Output written on MarsRAG.pdf (14 pages, 383292 bytes).
Output written on MarsRAG.pdf (14 pages, 384380 bytes).
PDF statistics: PDF statistics:
175 PDF objects out of 1000 (max. 8388607) 175 PDF objects out of 1000 (max. 8388607)
0 named destinations out of 1000 (max. 500000) 0 named destinations out of 1000 (max. 500000)

BIN
MarsRAG/MarsRAG.pdf
View File

Binary file not shown.

BIN
MarsRAG/MarsRAG.synctex.gz
View File

Binary file not shown.

31
MarsRAG/MarsRAG.tex
View File

@@ -54,34 +54,25 @@ Retrieval Augmented Generation, Planetary Remote Sensing, Hypergraph, Hyperbolic
Large Language Models (LLMs) have emerged as powerful tools for natural language understanding and generation \cite{Cai25LLM}, and Retrieval Augmented Generation (RAG) has been established as a standard paradigm for grounding LLM responses in external knowledge bases \cite{Lewis20RAG}. By dynamically retrieving relevant documents and conditioning generation on retrieved context, RAG effectively mitigates the hallucination problem inherent in LLMs and enables knowledge-intensive question answering \cite{Zhou24hallucination}. The synergy between LLMs and Knowledge Graphs (KGs) has further advanced retrieval performance through structured knowledge representation, achieving notable improvements in multi-hop reasoning, credibility assessment, and interpretability \cite{Pan24KGandLLM}. Large Language Models (LLMs) have emerged as powerful tools for natural language understanding and generation \cite{Cai25LLM}, and Retrieval Augmented Generation (RAG) has been established as a standard paradigm for grounding LLM responses in external knowledge bases \cite{Lewis20RAG}. By dynamically retrieving relevant documents and conditioning generation on retrieved context, RAG effectively mitigates the hallucination problem inherent in LLMs and enables knowledge-intensive question answering \cite{Zhou24hallucination}. The synergy between LLMs and Knowledge Graphs (KGs) has further advanced retrieval performance through structured knowledge representation, achieving notable improvements in multi-hop reasoning, credibility assessment, and interpretability \cite{Pan24KGandLLM}.
Nevertheless, deploying RAG systems for planetary science knowledge retrieval introduces domain-specific complexities that fundamentally challenge existing frameworks. Unlike conventional multi-source retrieval scenarios (e.g., integrating flight records, financial reports, or web documents), planetary observation data possesses two distinctive characteristics. First, all data sources are spatially grounded: each observation is anchored to a specific spatial footprint on the Martian surface, a temporal acquisition window parameterized by Solar Longitude ($L_s$), and instrument-specific parameters such as spectral bands and spatial resolution. The relevance between two observations is therefore governed not merely by textual semantic similarity, but primarily by physical spatial proximity, temporal co-occurrence, and cross-resolution complementarity. Second, inter-source inconsistencies in planetary science are not exclusively indicative of data errors or model hallucinations; rather, they frequently arise as inherent consequences of multi-platform, multi-scale observation and may encode critical scientific discoveries — such as subsurface geological evolution revealed by discrepancies between orbital spectroscopy and in-situ drilling results. % TODO：还要将多源数据过度一下
Nevertheless, deploying RAG systems for planetary science knowledge retrieval introduces domain-specific complexities that fundamentally challenge existing frameworks. Recent advances in multi-source RAG, exemplified by MultiRAG \cite{Wu25MultiRAG}, have made significant progress through multi-source line graphs and multi-level confidence computation. However, when confronted with planetary spatial data, these methods encounter two fundamental problems that cannot be resolved through parameter tuning alone:
Recent advances in multi-source RAG, exemplified by MultiRAG \cite{Wu25MultiRAG}, have made significant progress in addressing data sparsity and inter-source inconsistency through multi-source line graphs and multi-level confidence computation. However, when confronted with planetary spatial data, these methods encounter two structural bottlenecks that cannot be resolved through parameter tuning alone.
Building upon the analysis of existing multi-source RAG limitations [14]-[16] in the context of planetary science, we identify the following failure modes that are unique to spatially grounded, physically observed multi-source data:
\begin{enumerate}
\item Spatial topology distortion: When multi-source observations share no common textual entities but are spatially co-located, discrete line graphs fail to establish connectivity, resulting in fragmented retrieval.
\item Scale hierarchy collapse: Observations at different spatial resolutions (e.g., 0.3 m vs. 460 m) exhibit a natural hierarchical containment structure that flat graph topologies cannot represent, leading to loss of cross-resolution context during aggregation.
\item Scientifically valuable conflict suppression: Confidence-based conflict filtering indiscriminately eliminates disagreeing nodes, destroying observational evidence that may indicate genuine geological phenomena such as subsurface mineral heterogeneity.
\end{enumerate}
These failure modes trace back to two fundamental scientific problems:
\begin{enumerate} \begin{enumerate}
\item Problem 1: Discrete Representation Failure for Continuous Spatiotemporal Topology.** Existing multi-source knowledge aggregation methods, such as multi-source line graphs [14], rely on discrete text entities and explicit semantic associations to construct graph topology. However, planetary science data is intrinsically embedded in continuous Euclidean physical space. Attempting to encode continuous spatial proximity and directional relationships within traditional discrete graph structures inevitably triggers an edge explosion problem — $k$ co-located spatial entities require $\binom{k}{2} = O(k^2)$ pairwise spatial proximity edges — thereby destroying the optimizations that existing graph models achieve for data sparsity. The discrete logical graph structure thus constitutes a structural bottleneck constraining planetary spatial reasoning capabilities, unable to bridge the chasm between physical continuity and semantic discreteness. \item \textbf{The Spatial Topology Loss Problem.} Conventional multi-source retrieval systems judge relevance by textual semantic similarity. Planetary observations are different. Each observation is tied to a spatial footprint on the surface, a time window, and a set of instrument parameters. Two observations are relevant to each other mainly because they are spatially close, temporally overlapping, or captured at complementary resolutions. Existing methods such as multi-source line graphs \cite{Wu25MultiRAG} build graph topology from discrete text entities. This design creates a mismatch with continuous spatial data: $k$ co-located entities need $\binom{k}{2} = O(k^2)$ pairwise edges to represent their spatial relationships. The resulting edge explosion removes the sparsity that these graph models rely on. In short, the discrete graph structure cannot bridge the gap between physical continuity and semantic discreteness.
\item Problem 2: Fundamental Conflict Between Scientific Cognitive Divergence and Traditional De-Falsification Mechanisms.** The core assumption underlying existing multi-source RAG frameworks is that inter-source data inconsistency typically originates from misinformation or model hallucinations, and therefore relies on multi-level confidence computation to eliminate conflicting nodes [14], [17]. However, in deep-space exploration scenarios, the absence of absolute ground truth means that different observation platforms (e.g., orbiters versus rovers), due to differences in observation scale, penetration depth, and instrumental principles, often produce significantly conflicting results for the same target region. For instance, orbital spectrometers may detect surface hydrated minerals while in-situ drilling reveals no anomaly — a conflict arising not from data error, but from the inherent multi-dimensional nature of scientific observation, potentially harboring clues to major discoveries such as geological evolution. Applying existing conflict-filtering mechanisms indiscriminately would cause severe over-smoothing, uniformly suppressing high-value scientific anomalies and fundamentally violating the epistemological principle of deep-space exploration: preserving controversy and enabling multi-source corroboration for knowledge discovery.
\item \textbf{The Conflict Over-Smoothing Problem.} Existing multi-source RAG frameworks treat inter-source inconsistency as misinformation or hallucination. They use confidence scores to remove conflicting nodes \cite{Wu25MultiRAG}, \cite{Wang25Astute}. In planetary science, however, different platforms naturally produce different measurements for the same target. An orbiter and a rover observe at different scales, depths, and wavelengths. For example, an orbital spectrometer may detect hydrated minerals on the surface, while an in-situ drill finds olivine-carbonate assemblages below. This conflict does not come from data error. It reflects geological evolution across depth. If we apply uniform conflict filtering, the system suppresses these scientifically valuable signals together with genuine noise. This over-smoothing violates a core principle of deep-space exploration: observational disagreements should be preserved, because they may lead to new discoveries through multi-source comparison.
\end{enumerate} \end{enumerate}
To address these two fundamental challenges, we propose AreoRAG, a novel framework specifically designed for multi-source planetary spatial data retrieval augmented generation. AreoRAG introduces two synergistic innovations. First, to resolve Problem 1, we construct a Hyperbolic Spatial Hypergraph (HySH) that employs $n$-ary spatial observation hyperedges to bind co-located multi-source observations into single high-order facts, reducing edge complexity from $O(k^2)$ to $O(k)$. These hyperedges are embedded in hyperbolic space via the Lorentz model, where the exponential volume growth of negative-curvature geometry naturally accommodates the hierarchical scale structure of planetary observations — coarse-resolution global data resides near the origin while fine-resolution local data extends toward the boundary. Second, to resolve Problem 2, we develop a Physics-Informed Conflict Triage (PICT) mechanism that replaces the uniform conflict-filtering paradigm with a differentiated triage approach. PICT detects inter-source conflicts through cross-source interaction entropy, classifies each conflict into one of four physically grounded categories (noise, instrument-inherent, scale-dependent, temporal-evolution), and applies category-specific confidence recalibration — filtering genuine noise while provably preserving and even boosting the confidence of scientifically valuable observational disagreements. Together, HySH provides spatially faithful multi-source evidence to PICT, while PICT feeds back triage results to prioritize scientifically interesting regions in subsequent retrieval, forming a tightly coupled framework. To address these two challenges, we propose AreoRAG, a framework designed for multi-source planetary spatial data retrieval augmented generation. AreoRAG introduces two innovations. We first construct a \textbf{Hyperbolic Spatial Hypergraph (HySH)} to resolve the spatial topology loss problem. HySH uses $n$-ary spatial observation hyperedges to group co-located multi-source observations into single high-order facts. This design reduces edge complexity from $O(k^2)$ to $O(k)$. We embed these hyperedges in hyperbolic space via the Lorentz model. The exponential volume growth of negative-curvature geometry naturally fits the hierarchical scale structure of planetary observations. Coarse-resolution global data resides near the origin, while fine-resolution local data extends toward the boundary. To resolve the conflict over-smoothing problem, we develop a \textbf{Physics-Informed Conflict Triage (PICT)} mechanism. PICT replaces uniform conflict filtering with a differentiated triage strategy. It first detects inter-source conflicts through cross-source interaction entropy. Then it classifies each conflict into one of four physically grounded categories: noise, instrument-inherent, scale-dependent, and temporal-evolution. Finally, it applies category-specific confidence recalibration, filtering genuine noise while provably preserving scientifically valuable observational disagreements. The two modules form a tightly coupled loop. HySH provides spatially faithful multi-source evidence to PICT, while PICT feeds back triage results to prioritize scientifically interesting regions in subsequent retrieval.
The contributions of this paper are summarized as follows: The contributions of this paper are summarized as follows:
\begin{enumerate} \begin{enumerate}
\item Hyperbolic Spatial Hypergraph Construction: We introduce HySH, a knowledge construction module that employs $n$-ary spatial observation hyperedges embedded in hyperbolic space to achieve unified spatiotemporal representation of multi-source planetary data. By coupling spatial resolution with hyperbolic radial depth via the Lorentz model, HySH faithfully preserves the hierarchical scale structure of planetary observations while eliminating edge explosion through high-order relational encoding. A resolution-aware Spatial Outward Einstein Midpoint (Spatial OEM) aggregation operator is further proposed to prevent hierarchical collapse during cross-resolution evidence fusion, with a formal guarantee of outward bias. \item{We propose a Hyperbolic Spatial Hypergraph (HySH) construction module for multi-source planetary data, by combining the $n$-ary hyperedge representation from hypergraph-based RAG \cite{placeholder_HyperRAG} with the Lorentz-model hyperbolic embedding from hyperbolic knowledge graph methods \cite{placeholder_HypRAG}. HySH couples spatial resolution with hyperbolic radial depth so that the hierarchical scale structure of planetary observations is preserved, while edge complexity is reduced from $O(k^2)$ to $O(k)$. We further propose a resolution-aware Spatial Outward Einstein Midpoint (Spatial OEM) aggregation operator with a formal guarantee of outward bias.}
\item Physics-Informed Conflict Triage: We propose PICT, a retrieval module that fundamentally redefines the role of inter-source conflict in RAG systems. Through cross-source interaction entropy for conflict detection, a physically grounded four-category conflict classification informed by observation geometry, and differentiated confidence recalibration, PICT provably prevents the over-smoothing of scientifically valuable disagreements (Anti-Over-Smoothing Guarantee) while maintaining noise-filtering capability. To the best of our knowledge, this is the first conflict-handling mechanism in RAG that explicitly distinguishes between erroneous inconsistency and scientifically meaningful observational divergence. \item{We propose a Physics-Informed Conflict Triage (PICT) mechanism for multi-source retrieval, by adapting the entropy-based conflict detection from \cite{placeholder_TruthfulRAG} and the linear-separability finding of knowledge conflicts from \cite{placeholder_Diagnosing}. PICT classifies each inter-source conflict into four physically grounded categories (noise, instrument-inherent, scale-dependent, temporal-evolution) and applies category-specific confidence recalibration. We provide a formal Anti-Over-Smoothing Guarantee showing that scientifically valuable disagreements are provably preserved. To the best of our knowledge, this is the first conflict-handling mechanism in RAG that explicitly distinguishes erroneous inconsistency from scientifically meaningful observational divergence.}
\item Integrated Framework and Experimental Validation: We design the AreoRAG Prompting (ARP) algorithm that integrates HySH and PICT through three explicit coupling points: spatial alignment as a prerequisite for interaction entropy computation, radial depth difference as a resolution disparity signal for conflict classification, and triage-driven retrieval priority feedback. Extensive experiments on multi-source planetary observation datasets demonstrate that AreoRAG significantly outperforms existing multi-source RAG methods in both retrieval fidelity and scientific faithfulness, with particular advantages in scenarios involving cross-resolution reasoning and observation-grounded conflict preservation. \item{We design the AreoRAG Prompting (ARP) algorithm that integrates HySH and PICT through three coupling points: spatial alignment as a prerequisite for interaction entropy computation, radial depth difference as a resolution disparity signal for conflict classification, and triage-driven retrieval priority feedback. Experiments on three Mars observation datasets show that AreoRAG outperforms existing multi-source RAG methods in both retrieval accuracy and conflict preservation.}
\end{enumerate} \end{enumerate}
\section{Preliminary} \section{Preliminary}

BIN
MarsRAG/fig1.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 37 KiB

20
MarsRAG/references.bib
View File

@@ -346,3 +346,23 @@
location = {Singapore, Singapore}, location = {Singapore, Singapore},
series = {WWW '24} series = {WWW '24}
} }
@inproceedings{Wang25Astute,
title = "Astute {RAG}: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models",
author = "Wang, Fei and
Wan, Xingchen and
Sun, Ruoxi and
Chen, Jiefeng and
Arik, Sercan O",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
pages = "30553--30571",
ISBN = "979-8-89176-251-0",
}

12
paper_introduction.md
View File

@@ -20,17 +20,7 @@ Large Language Models (LLMs) have emerged as powerful tools for natural language
Nevertheless, deploying RAG systems for planetary science knowledge retrieval introduces domain-specific complexities that fundamentally challenge existing frameworks. Unlike conventional multi-source retrieval scenarios (e.g., integrating flight records, financial reports, or web documents), planetary observation data possesses two distinctive characteristics. First, all data sources are spatially grounded: each observation is anchored to a specific spatial footprint on the Martian surface, a temporal acquisition window parameterized by Solar Longitude ($L_s$), and instrument-specific parameters such as spectral bands and spatial resolution. The relevance between two observations is therefore governed not merely by textual semantic similarity, but primarily by physical spatial proximity, temporal co-occurrence, and cross-resolution complementarity. Second, inter-source inconsistencies in planetary science are not exclusively indicative of data errors or model hallucinations; rather, they frequently arise as inherent consequences of multi-platform, multi-scale observation and may encode critical scientific discoveries — such as subsurface geological evolution revealed by discrepancies between orbital spectroscopy and in-situ drilling results. Nevertheless, deploying RAG systems for planetary science knowledge retrieval introduces domain-specific complexities that fundamentally challenge existing frameworks. Unlike conventional multi-source retrieval scenarios (e.g., integrating flight records, financial reports, or web documents), planetary observation data possesses two distinctive characteristics. First, all data sources are spatially grounded: each observation is anchored to a specific spatial footprint on the Martian surface, a temporal acquisition window parameterized by Solar Longitude ($L_s$), and instrument-specific parameters such as spectral bands and spatial resolution. The relevance between two observations is therefore governed not merely by textual semantic similarity, but primarily by physical spatial proximity, temporal co-occurrence, and cross-resolution complementarity. Second, inter-source inconsistencies in planetary science are not exclusively indicative of data errors or model hallucinations; rather, they frequently arise as inherent consequences of multi-platform, multi-scale observation and may encode critical scientific discoveries — such as subsurface geological evolution revealed by discrepancies between orbital spectroscopy and in-situ drilling results.
Recent advances in multi-source RAG, exemplified by MultiRAG [14], have made significant progress in addressing data sparsity and inter-source inconsistency through multi-source line graphs and multi-level confidence computation. However, when confronted with planetary spatial data, these methods encounter two structural bottlenecks that cannot be resolved through parameter tuning alone. Recent advances in multi-source RAG, exemplified by MultiRAG [14], have made significant progress in addressing data sparsity and inter-source inconsistency through multi-source line graphs and multi-level confidence computation. However, when confronted with planetary spatial data, these methods encounter two fundamental problems that cannot be resolved through parameter tuning alone:
Building upon the analysis of existing multi-source RAG limitations [14]-[16] in the context of planetary science, we identify the following failure modes that are unique to spatially grounded, physically observed multi-source data:
1) **Spatial topology distortion**: When multi-source observations share no common textual entities but are spatially co-located, discrete line graphs fail to establish connectivity, resulting in fragmented retrieval.
2) **Scale hierarchy collapse**: Observations at different spatial resolutions (e.g., 0.3 m vs. 460 m) exhibit a natural hierarchical containment structure that flat graph topologies cannot represent, leading to loss of cross-resolution context during aggregation.
3) **Scientifically valuable conflict suppression**: Confidence-based conflict filtering indiscriminately eliminates disagreeing nodes, destroying observational evidence that may indicate genuine geological phenomena such as subsurface mineral heterogeneity.
These failure modes trace back to two fundamental scientific problems:
**Problem 1: Discrete Representation Failure for Continuous Spatiotemporal Topology.** Existing multi-source knowledge aggregation methods, such as multi-source line graphs [14], rely on discrete text entities and explicit semantic associations to construct graph topology. However, planetary science data is intrinsically embedded in continuous Euclidean physical space. Attempting to encode continuous spatial proximity and directional relationships within traditional discrete graph structures inevitably triggers an edge explosion problem — $k$ co-located spatial entities require $\binom{k}{2} = O(k^2)$ pairwise spatial proximity edges — thereby destroying the optimizations that existing graph models achieve for data sparsity. The discrete logical graph structure thus constitutes a structural bottleneck constraining planetary spatial reasoning capabilities, unable to bridge the chasm between physical continuity and semantic discreteness. **Problem 1: Discrete Representation Failure for Continuous Spatiotemporal Topology.** Existing multi-source knowledge aggregation methods, such as multi-source line graphs [14], rely on discrete text entities and explicit semantic associations to construct graph topology. However, planetary science data is intrinsically embedded in continuous Euclidean physical space. Attempting to encode continuous spatial proximity and directional relationships within traditional discrete graph structures inevitably triggers an edge explosion problem — $k$ co-located spatial entities require $\binom{k}{2} = O(k^2)$ pairwise spatial proximity edges — thereby destroying the optimizations that existing graph models achieve for data sparsity. The discrete logical graph structure thus constitutes a structural bottleneck constraining planetary spatial reasoning capabilities, unable to bridge the chasm between physical continuity and semantic discreteness.