修改方法部分
This commit is contained in:
龙澳
@@ -25,6 +25,7 @@
|
||||
\newlabel{equ:hyperbolic space}{{4}{3}}
|
||||
\@writefile{toc}{\contentsline {section}{\numberline {III}Methodology}{3}{}\protected@file@percent }
|
||||
\@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {III-A}}Framework of AreoRAG}{3}{}\protected@file@percent }
|
||||
\citation{luo25hyperrag}
|
||||
\@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {III-B}}Hyperbolic Spatial Hypergraph Construction}{4}{}\protected@file@percent }
|
||||
\newlabel{sec:HySH}{{\mbox {III-B}}{4}}
|
||||
\newlabel{equ:multi-source spatial data}{{5}{4}}
|
||||
@@ -34,13 +35,27 @@
|
||||
\@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {III-C}}Spatiotemporal Retrieval with Cross-Resolution Aggregation}{4}{}\protected@file@percent }
|
||||
\newlabel{sec:retrieval}{{\mbox {III-C}}{4}}
|
||||
\newlabel{equ:Spatial Intent Extraction and Hyperedge Retrieval}{{9}{4}}
|
||||
\citation{Li25SubGraphRAG}
|
||||
\citation{luo25hyperrag}
|
||||
\citation{madhu26hyprag}
|
||||
\citation{liu26truthfulrag}
|
||||
\newlabel{equ:spatiotemporal encoding}{{10}{5}}
|
||||
\newlabel{equ:hyperbolic spatial encoding}{{11}{5}}
|
||||
\newlabel{equ:MLP scores}{{12}{5}}
|
||||
\newlabel{equ:Spatial OEM}{{13}{5}}
|
||||
\newlabel{equ:Spatial OEM Outward Bias}{{14}{5}}
|
||||
\@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {III-D}}Physics-Informed Conflict Triage}{5}{}\protected@file@percent }
|
||||
\newlabel{sec:PICT}{{\mbox {III-D}}{5}}
|
||||
\newlabel{equ:interaction entropy}{{15}{5}}
|
||||
\newlabel{equ:token-averaged entropy}{{16}{5}}
|
||||
\newlabel{equ:conflict detection}{{17}{5}}
|
||||
\newlabel{equ:explainable conflict}{{18}{5}}
|
||||
\@writefile{lot}{\contentsline {table}{\numberline {I}{\ignorespaces Physics-Informed Conflict Triage Categories}}{6}{}\protected@file@percent }
|
||||
\newlabel{table_conflict_triage}{{I}{6}}
|
||||
\newlabel{equ:conflict classification feature vector}{{19}{6}}
|
||||
\newlabel{equ:conflict classification}{{20}{6}}
|
||||
\newlabel{equ:conflict classification}{{21}{6}}
|
||||
\newlabel{equ:Anti-Over-Smoothing Guarantee}{{22}{6}}
|
||||
\@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {III-E}}AreoRAG Prompting}{6}{}\protected@file@percent }
|
||||
\newlabel{sec:prompt}{{\mbox {III-E}}{6}}
|
||||
\@writefile{loa}{\contentsline {algorithm}{\numberline {1}{\ignorespaces AreoRAG Prompting (ARP)}}{6}{}\protected@file@percent }
|
||||
@@ -89,4 +104,5 @@
|
||||
\bibcite{madhu26hyprag}{14}
|
||||
\bibcite{liu26truthfulrag}{15}
|
||||
\bibcite{tang26diagnosing}{16}
|
||||
\bibcite{Li25SubGraphRAG}{17}
|
||||
\gdef \@abspage@last{14}
|
||||
|
||||
@@ -133,4 +133,11 @@ J.~Tang, K.~Wang, H.~Lu, H.~Chen, K.~Chen, Z.~Sun, Q.~Li, L.~Lyu, G.~Nan, and
|
||||
Z.~Zeng, ``Diagnosing knowledge conflict in multimodal long-chain
|
||||
reasoning,'' \emph{arXiv preprint arXiv:2602.14518}, 2026.
|
||||
|
||||
\bibitem{Li25SubGraphRAG}
|
||||
M.~Li, S.~Miao, and P.~Li, ``Simple is effective: The roles of graphs and large
|
||||
language models in knowledge-graph-based retrieval-augmented generation,'' in
|
||||
\emph{The Thirteenth International Conference on Learning Representations,
|
||||
{ICLR} 2025, Singapore, April 24-28, 2025}.\hskip 1em plus 0.5em minus
|
||||
0.4em\relax OpenReview.net, 2025.
|
||||
|
||||
\end{thebibliography}
|
||||
|
||||
@@ -17,44 +17,44 @@ Database file #2: references.bib
|
||||
-- See the "IEEEtran_bst_HOWTO.pdf" manual for usage information.
|
||||
|
||||
Done.
|
||||
You've used 16 entries,
|
||||
You've used 17 entries,
|
||||
4087 wiz_defined-function locations,
|
||||
1714 strings with 29245 characters,
|
||||
and the built_in function-call counts, 17086 in all, are:
|
||||
= -- 1126
|
||||
> -- 897
|
||||
1720 strings with 29554 characters,
|
||||
and the built_in function-call counts, 17601 in all, are:
|
||||
= -- 1159
|
||||
> -- 910
|
||||
< -- 74
|
||||
+ -- 471
|
||||
- -- 225
|
||||
* -- 891
|
||||
:= -- 2223
|
||||
add.period$ -- 35
|
||||
call.type$ -- 16
|
||||
change.case$ -- 18
|
||||
+ -- 477
|
||||
- -- 228
|
||||
* -- 914
|
||||
:= -- 2301
|
||||
add.period$ -- 38
|
||||
call.type$ -- 17
|
||||
change.case$ -- 19
|
||||
chr.to.int$ -- 159
|
||||
cite$ -- 16
|
||||
duplicate$ -- 1212
|
||||
empty$ -- 1268
|
||||
format.name$ -- 224
|
||||
if$ -- 3991
|
||||
cite$ -- 17
|
||||
duplicate$ -- 1258
|
||||
empty$ -- 1330
|
||||
format.name$ -- 228
|
||||
if$ -- 4113
|
||||
int.to.chr$ -- 0
|
||||
int.to.str$ -- 16
|
||||
missing$ -- 308
|
||||
newline$ -- 71
|
||||
num.names$ -- 18
|
||||
pop$ -- 825
|
||||
int.to.str$ -- 17
|
||||
missing$ -- 318
|
||||
newline$ -- 74
|
||||
num.names$ -- 19
|
||||
pop$ -- 854
|
||||
preamble$ -- 1
|
||||
purify$ -- 0
|
||||
quote$ -- 2
|
||||
skip$ -- 1221
|
||||
skip$ -- 1260
|
||||
stack$ -- 0
|
||||
substring$ -- 491
|
||||
swap$ -- 1016
|
||||
substring$ -- 492
|
||||
swap$ -- 1040
|
||||
text.length$ -- 21
|
||||
text.prefix$ -- 0
|
||||
top$ -- 5
|
||||
type$ -- 16
|
||||
type$ -- 17
|
||||
warning$ -- 0
|
||||
while$ -- 37
|
||||
width$ -- 18
|
||||
write$ -- 174
|
||||
while$ -- 38
|
||||
width$ -- 19
|
||||
write$ -- 182
|
||||
|
||||
@@ -1,14 +1,14 @@
|
||||
# Fdb version 4
|
||||
["bibtex MarsRAG"] 1775630125.41037 "MarsRAG.aux" "MarsRAG.bbl" "MarsRAG" 1775630127.34957 0
|
||||
"./references.bib" 1775562768.48604 20554 9d70dc88ee020645ea0e5a2a02870f06 ""
|
||||
["bibtex MarsRAG"] 1775632489.46607 "MarsRAG.aux" "MarsRAG.bbl" "MarsRAG" 1775632696.24948 0
|
||||
"./references.bib" 1775631546.85579 21060 cb755e3d069bfb993edf430f576e97e4 ""
|
||||
"D:/software/ctex/MiKTeX/bibtex/bib/ieeetran/IEEEabrv.bib" 1440617548 20898 a5d2167c380db7dfff810b085c77ed63 ""
|
||||
"D:/software/ctex/MiKTeX/bibtex/bst/ieeetran/IEEEtran.bst" 1440622569 57748 7c8250ecf02814ce6ddc0cdbb63df1dd ""
|
||||
"MarsRAG.aux" 1775630126.42582 6070 d6ae3bd429cbef8661ced5f0a1f8718b "pdflatex"
|
||||
"MarsRAG.aux" 1775632695.3425 6707 a13591f13f0356ed038e62f2e3954e3b "pdflatex"
|
||||
(generated)
|
||||
"MarsRAG.bbl"
|
||||
"MarsRAG.blg"
|
||||
(rewritten before read)
|
||||
["pdflatex"] 1775630125.69247 "d:/onedrive/Desktop/Multi-RAG/MarsRAG/MarsRAG.tex" "MarsRAG.pdf" "MarsRAG" 1775630127.35067 0
|
||||
["pdflatex"] 1775632694.59958 "d:/onedrive/Desktop/Multi-RAG/MarsRAG/MarsRAG.tex" "MarsRAG.pdf" "MarsRAG" 1775632696.25065 0
|
||||
"D:/software/ctex/CTeX/fonts/sfd/UGBK.sfd" 1241576166 185529 821b4d3a4d64ce6f0757b41592552808 ""
|
||||
"D:/software/ctex/CTeX/fonts/sfd/Unicode.sfd" 1241576166 5003 ada6fc83625c51dfd3000a816ae41161 ""
|
||||
"D:/software/ctex/MiKTeX/fonts/enc/dvips/base/8r.enc" 1458473886 4993 1194fb36dfcb11d9ae9802f2b00b60a3 ""
|
||||
@@ -121,9 +121,9 @@
|
||||
"D:/software/ctex/MiKTeX/tex/latex/url/url.sty" 1388490452 12796 8edb7d69a20b857904dd0ea757c14ec9 ""
|
||||
"D:/software/ctex/UserData/fonts/map/pdftex/pdftex.map" 1775617581.10787 280574 11b05735ccd5db23e8baf414abaacaec ""
|
||||
"D:/software/ctex/UserData/miktex/data/le/pdftex/pdflatex.fmt" 1761184910.39527 23169076 a8cfad5eb3d5cf02ce2e7aad0517b308 ""
|
||||
"MarsRAG.aux" 1775630126.42582 6070 d6ae3bd429cbef8661ced5f0a1f8718b "pdflatex"
|
||||
"MarsRAG.bbl" 1775630125.62977 6984 fa9ed0490fb69514c7798dd23755293b "bibtex MarsRAG"
|
||||
"d:/onedrive/Desktop/Multi-RAG/MarsRAG/MarsRAG.tex" 1775615879.68487 84291 5c2cb769f342a19bd671147b8b172f67 ""
|
||||
"MarsRAG.aux" 1775632695.3425 6707 a13591f13f0356ed038e62f2e3954e3b "pdflatex"
|
||||
"MarsRAG.bbl" 1775632489.67722 7364 b7a485e756f8a1d65e4cec99e531b487 "bibtex MarsRAG"
|
||||
"d:/onedrive/Desktop/Multi-RAG/MarsRAG/MarsRAG.tex" 1775632693.94638 85154 5f21c8829e6299d9a2ee36bb0f37039b ""
|
||||
(generated)
|
||||
"MarsRAG.aux"
|
||||
"MarsRAG.log"
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
This is pdfTeX, Version 3.141592653-2.6-1.40.25 (MiKTeX 23.4) (preloaded format=pdflatex 2025.10.23) 8 APR 2026 14:35
|
||||
This is pdfTeX, Version 3.141592653-2.6-1.40.25 (MiKTeX 23.4) (preloaded format=pdflatex 2025.10.23) 8 APR 2026 15:18
|
||||
entering extended mode
|
||||
restricted \write18 enabled.
|
||||
file:line:error style messages enabled.
|
||||
@@ -292,7 +292,11 @@ File: l3backend-pdftex.def 2023-03-30 L3 backend support: PDF output (pdfTeX)
|
||||
LaTeX Warning: Unused global option(s):
|
||||
[lettersize].
|
||||
|
||||
(MarsRAG.aux)
|
||||
(MarsRAG.aux
|
||||
|
||||
LaTeX Warning: Label `equ:conflict classification' multiply defined.
|
||||
|
||||
)
|
||||
\openout1 = `MarsRAG.aux'.
|
||||
|
||||
LaTeX Font Info: Checking defaults for OML/cmm/m/it on input line 18.
|
||||
@@ -363,242 +367,289 @@ Overfull \hbox (4.88393pt too wide) detected at line 149
|
||||
[][] []\OML/cmm/m/it/10 :
|
||||
[]
|
||||
|
||||
[4]
|
||||
Overfull \hbox (9.20645pt too wide) detected at line 194
|
||||
|
||||
Overfull \hbox (9.20645pt too wide) detected at line 193
|
||||
[]\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 199
|
||||
[4]
|
||||
Overfull \hbox (2.51953pt too wide) detected at line 198
|
||||
[]\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 ;
|
||||
[]
|
||||
|
||||
|
||||
Underfull \hbox (badness 10000) in paragraph at lines 210--211
|
||||
Underfull \hbox (badness 10000) in paragraph at lines 209--210
|
||||
[]\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 210--211
|
||||
Underfull \hbox (badness 3895) in paragraph at lines 209--210
|
||||
\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 weights $\OML/cmm/m/it/10 w[]$
|
||||
[]
|
||||
|
||||
|
||||
Overfull \hbox (113.53706pt too wide) detected at line 232
|
||||
\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 ^^@ [] [] \OML/cmm/m/it/10 ;
|
||||
Overfull \hbox (113.53706pt too wide) detected at line 235
|
||||
[]\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 ^^@ [] [] \OML/cmm/m/it/10 ;
|
||||
[]
|
||||
|
||||
[5]
|
||||
Overfull \hbox (41.67476pt too wide) in paragraph at lines 259--273
|
||||
Underfull \hbox (badness 10000) in paragraph at lines 270--270
|
||||
|[]
|
||||
[]
|
||||
|
||||
|
||||
Overfull \hbox (3.69943pt too wide) in paragraph at lines 270--270
|
||||
[]
|
||||
[]
|
||||
|
||||
|
||||
Underfull \hbox (badness 10000) in paragraph at lines 272--272
|
||||
|[]
|
||||
[]
|
||||
|
||||
|
||||
Overfull \hbox (4.2324pt too wide) in paragraph at lines 272--272
|
||||
[]
|
||||
[]
|
||||
|
||||
|
||||
Underfull \hbox (badness 10000) in paragraph at lines 274--275
|
||||
|[]
|
||||
[]
|
||||
|
||||
|
||||
Overfull \hbox (2.67535pt too wide) in paragraph at lines 274--275
|
||||
[]
|
||||
[]
|
||||
|
||||
|
||||
Underfull \hbox (badness 10000) in paragraph at lines 276--276
|
||||
|[]
|
||||
[]
|
||||
|
||||
|
||||
Overfull \hbox (4.85658pt too wide) in paragraph at lines 276--276
|
||||
[]
|
||||
[]
|
||||
|
||||
|
||||
Overfull \hbox (4.68652pt too wide) in paragraph at lines 265--279
|
||||
[][]
|
||||
[]
|
||||
|
||||
|
||||
Overfull \hbox (49.71666pt too wide) detected at line 277
|
||||
\OT1/cmr/bx/n/10 z[] \OT1/cmr/m/n/10 = []
|
||||
Overfull \hbox (54.16107pt too wide) detected at line 285
|
||||
[]\OT1/cmr/bx/n/10 z[] \OT1/cmr/m/n/10 = [] \OML/cmm/m/it/10 ;
|
||||
[]
|
||||
|
||||
|
||||
Overfull \hbox (10.51593pt too wide) detected at line 289
|
||||
\OML/cmm/m/it/10 C[]\OT1/cmr/m/n/10 (\OML/cmm/m/it/10 v\OT1/cmr/m/n/10 ) = []
|
||||
Overfull \hbox (13.68317pt too wide) detected at line 305
|
||||
[]\OML/cmm/m/it/10 C[] [] \OT1/cmr/m/n/10 = []
|
||||
[]
|
||||
|
||||
LaTeX Font Info: Trying to load font information for OMS+ptm on input line 312.
|
||||
(D:\software\ctex\MiKTeX\tex/latex/psnfss\omsptm.fd
|
||||
|
||||
Underfull \vbox (badness 6173) has occurred while \output is active []
|
||||
|
||||
LaTeX Font Info: Trying to load font information for OMS+ptm on input line 329.
|
||||
(D:\software\ctex\MiKTeX\tex/latex/psnfss\omsptm.fd
|
||||
File: omsptm.fd
|
||||
)
|
||||
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 312.
|
||||
(Font) Font shape `OMS/cmsy/m/n' tried instead on input line 329.
|
||||
[6]
|
||||
Underfull \hbox (badness 10000) in paragraph at lines 366--366
|
||||
Underfull \hbox (badness 10000) in paragraph at lines 383--383
|
||||
|[]
|
||||
[]
|
||||
|
||||
|
||||
Overfull \hbox (14.39503pt too wide) in paragraph at lines 366--366
|
||||
Overfull \hbox (14.39503pt too wide) in paragraph at lines 383--383
|
||||
[]
|
||||
[]
|
||||
|
||||
|
||||
Underfull \hbox (badness 10000) in paragraph at lines 366--366
|
||||
Underfull \hbox (badness 10000) in paragraph at lines 383--383
|
||||
|[]
|
||||
[]
|
||||
|
||||
|
||||
Overfull \hbox (11.8429pt too wide) in paragraph at lines 366--366
|
||||
Overfull \hbox (11.8429pt too wide) in paragraph at lines 383--383
|
||||
[]
|
||||
[]
|
||||
|
||||
|
||||
Overfull \hbox (25.19485pt too wide) in paragraph at lines 369--369
|
||||
Overfull \hbox (25.19485pt too wide) in paragraph at lines 386--386
|
||||
[]|[]|
|
||||
[]
|
||||
|
||||
|
||||
Underfull \hbox (badness 10000) in paragraph at lines 369--369
|
||||
Underfull \hbox (badness 10000) in paragraph at lines 386--386
|
||||
|[]
|
||||
[]
|
||||
|
||||
|
||||
Overfull \hbox (27.67467pt too wide) in paragraph at lines 369--369
|
||||
Overfull \hbox (27.67467pt too wide) in paragraph at lines 386--386
|
||||
[]
|
||||
[]
|
||||
|
||||
|
||||
Underfull \hbox (badness 10000) in paragraph at lines 371--371
|
||||
Underfull \hbox (badness 10000) in paragraph at lines 388--388
|
||||
|[]
|
||||
[]
|
||||
|
||||
|
||||
Overfull \hbox (18.33882pt too wide) in paragraph at lines 371--371
|
||||
Overfull \hbox (18.33882pt too wide) in paragraph at lines 388--388
|
||||
[]
|
||||
[]
|
||||
|
||||
|
||||
Underfull \hbox (badness 10000) in paragraph at lines 373--373
|
||||
Underfull \hbox (badness 10000) in paragraph at lines 390--390
|
||||
|[]
|
||||
[]
|
||||
|
||||
|
||||
Overfull \hbox (27.23465pt too wide) in paragraph at lines 373--373
|
||||
Overfull \hbox (27.23465pt too wide) in paragraph at lines 390--390
|
||||
[]
|
||||
[]
|
||||
|
||||
|
||||
Underfull \hbox (badness 10000) in paragraph at lines 375--375
|
||||
Underfull \hbox (badness 10000) in paragraph at lines 392--392
|
||||
|[]
|
||||
[]
|
||||
|
||||
|
||||
Overfull \hbox (25.89078pt too wide) in paragraph at lines 375--375
|
||||
Overfull \hbox (25.89078pt too wide) in paragraph at lines 392--392
|
||||
[]
|
||||
[]
|
||||
|
||||
|
||||
Underfull \hbox (badness 10000) in paragraph at lines 377--377
|
||||
Underfull \hbox (badness 10000) in paragraph at lines 394--394
|
||||
|[]
|
||||
[]
|
||||
|
||||
|
||||
Overfull \hbox (24.43471pt too wide) in paragraph at lines 377--377
|
||||
Overfull \hbox (24.43471pt too wide) in paragraph at lines 394--394
|
||||
[]
|
||||
[]
|
||||
|
||||
|
||||
Underfull \hbox (badness 10000) in paragraph at lines 377--377
|
||||
Underfull \hbox (badness 10000) in paragraph at lines 394--394
|
||||
|[]
|
||||
[]
|
||||
|
||||
|
||||
Overfull \hbox (30.10707pt too wide) in paragraph at lines 377--377
|
||||
Overfull \hbox (30.10707pt too wide) in paragraph at lines 394--394
|
||||
[]
|
||||
[]
|
||||
|
||||
|
||||
Underfull \hbox (badness 10000) in paragraph at lines 379--379
|
||||
Underfull \hbox (badness 10000) in paragraph at lines 396--396
|
||||
|[]
|
||||
[]
|
||||
|
||||
|
||||
Overfull \hbox (32.7467pt too wide) in paragraph at lines 379--379
|
||||
Overfull \hbox (32.7467pt too wide) in paragraph at lines 396--396
|
||||
[]
|
||||
[]
|
||||
|
||||
|
||||
Underfull \hbox (badness 10000) in paragraph at lines 379--379
|
||||
Underfull \hbox (badness 10000) in paragraph at lines 396--396
|
||||
|[]
|
||||
[]
|
||||
|
||||
|
||||
Overfull \hbox (30.10707pt too wide) in paragraph at lines 379--379
|
||||
Overfull \hbox (30.10707pt too wide) in paragraph at lines 396--396
|
||||
[]
|
||||
[]
|
||||
|
||||
|
||||
Underfull \hbox (badness 2452) in paragraph at lines 384--385
|
||||
Underfull \hbox (badness 2452) in paragraph at lines 401--402
|
||||
[]\OT1/ptm/m/n/10 Additionally, to val-i-date gen-er-al-iza-tion on es-tab-lished
|
||||
[]
|
||||
|
||||
[7]
|
||||
Underfull \hbox (badness 10000) in paragraph at lines 414--415
|
||||
Underfull \hbox (badness 10000) in paragraph at lines 431--432
|
||||
[]\OT1/ptm/m/n/10 1) **Stan-dard RAG** [6]: Con-ven-tional retrieval-
|
||||
[]
|
||||
|
||||
|
||||
Underfull \hbox (badness 1603) in paragraph at lines 424--425
|
||||
Underfull \hbox (badness 1603) in paragraph at lines 441--442
|
||||
[]\OT1/ptm/m/n/10 5) **Hy-per-GraphRAG** [25]: Hypergraph-based RAG
|
||||
[]
|
||||
|
||||
|
||||
Underfull \hbox (badness 2698) in paragraph at lines 478--479
|
||||
Underfull \hbox (badness 2698) in paragraph at lines 495--496
|
||||
\OT1/ptm/m/n/10 ti-HopQA), Are-oRAG main-tains com-pet-i-tive per-for-mance
|
||||
[]
|
||||
|
||||
[8]
|
||||
Underfull \hbox (badness 10000) in paragraph at lines 523--523
|
||||
Underfull \hbox (badness 10000) in paragraph at lines 540--540
|
||||
[]|\OT1/ptm/m/n/8 w/o In-ter-ac-tion En-tropy (use
|
||||
[]
|
||||
|
||||
|
||||
Underfull \hbox (badness 3271) in paragraph at lines 530--531
|
||||
Underfull \hbox (badness 3271) in paragraph at lines 547--548
|
||||
[]\OT1/ptm/m/n/10 **a) HySH Mod-ule Anal-y-sis:** The HySH mod-ule
|
||||
[]
|
||||
|
||||
|
||||
Underfull \hbox (badness 1917) in paragraph at lines 532--533
|
||||
Underfull \hbox (badness 1917) in paragraph at lines 549--550
|
||||
\OT1/ptm/m/n/10 F1 im-prove-ment over Eu-clidean hy-per-graph (49.2% vs.
|
||||
[]
|
||||
|
||||
[9]
|
||||
Underfull \hbox (badness 10000) in paragraph at lines 555--555
|
||||
Underfull \hbox (badness 10000) in paragraph at lines 572--572
|
||||
[]|\OT1/ptm/m/n/8 Standard
|
||||
[]
|
||||
|
||||
|
||||
Underfull \hbox (badness 10000) in paragraph at lines 557--557
|
||||
Underfull \hbox (badness 10000) in paragraph at lines 574--574
|
||||
[]|\OT1/ptm/m/n/8 MultiRAG
|
||||
[]
|
||||
|
||||
|
||||
Underfull \hbox (badness 10000) in paragraph at lines 563--563
|
||||
Underfull \hbox (badness 10000) in paragraph at lines 580--580
|
||||
[]|\OT1/ptm/b/n/8 AreoRAG
|
||||
[]
|
||||
|
||||
[10] [11]
|
||||
Package textcomp Info: Symbol \textrightarrow not provided by
|
||||
(textcomp) font family ptm in TS1 encoding.
|
||||
(textcomp) Default family used instead on input line 655.
|
||||
(textcomp) Default family used instead on input line 672.
|
||||
Package textcomp Info: Symbol \textrightarrow not provided by
|
||||
(textcomp) font family ptm in TS1 encoding.
|
||||
(textcomp) Default family used instead on input line 655.
|
||||
(textcomp) Default family used instead on input line 672.
|
||||
[12{D:/software/ctex/MiKTeX/fonts/enc/dvips/cm-super/cm-super-ts1.enc}]
|
||||
Underfull \hbox (badness 2495) in paragraph at lines 689--690
|
||||
Underfull \hbox (badness 2495) in paragraph at lines 706--707
|
||||
[]\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 689--690
|
||||
Underfull \hbox (badness 2799) in paragraph at lines 706--707
|
||||
\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 689--690
|
||||
Underfull \hbox (badness 7576) in paragraph at lines 706--707
|
||||
\OT1/ptm/m/n/10 ence and Tech-nol-ogy In-no-va-tion Co-op-er-a-tion" (Grant
|
||||
[]
|
||||
|
||||
(MarsRAG.bbl [13]) [14
|
||||
|
||||
] (MarsRAG.aux) )
|
||||
] (MarsRAG.aux)
|
||||
|
||||
LaTeX Warning: There were multiply-defined labels.
|
||||
|
||||
)
|
||||
Here is how much of TeX's memory you used:
|
||||
5485 strings out of 476331
|
||||
91488 string characters out of 5797649
|
||||
5495 strings out of 476331
|
||||
91763 string characters out of 5797649
|
||||
1892660 words of memory out of 5000000
|
||||
25830 multiletter control sequences out of 15000+600000
|
||||
25840 multiletter control sequences out of 15000+600000
|
||||
562405 words of font info for 135 fonts, out of 8000000 for 9000
|
||||
1145 hyphenation exceptions out of 8191
|
||||
57i,19n,63p,2307b,408s stack positions out of 10000i,1000n,20000p,200000b,200000s
|
||||
<D:/software/ctex/MiKTeX/fonts/type1/public/amsfonts/cm/cmbx10.pfb><D:/software/ctex/MiKTeX/fonts/type1/public/amsfonts/cm/cmbx7.pfb><D:/software/ctex/MiKTeX/fonts/type1/public/amsfonts/cm/cmex10.pfb><D:/software/ctex/MiKTeX/fonts/type1/public/amsfonts/cm/cmmi10.pfb><D:/software/ctex/MiKTeX/fonts/type1/public/amsfonts/cm/cmmi5.pfb><D:/software/ctex/MiKTeX/fonts/type1/public/amsfonts/cm/cmmi6.pfb><D:/software/ctex/MiKTeX/fonts/type1/public/amsfonts/cm/cmmi7.pfb><D:/software/ctex/MiKTeX/fonts/type1/public/amsfonts/cm/cmmi8.pfb><D:/software/ctex/MiKTeX/fonts/type1/public/amsfonts/cm/cmmi9.pfb><D:/software/ctex/MiKTeX/fonts/type1/public/amsfonts/cm/cmr10.pfb><D:/software/ctex/MiKTeX/fonts/type1/public/amsfonts/cm/cmr6.pfb><D:/software/ctex/MiKTeX/fonts/type1/public/amsfonts/cm/cmr7.pfb><D:/software/ctex/MiKTeX/fonts/type1/public/amsfonts/cm/cmr8.pfb><D:/software/ctex/MiKTeX/fonts/type1/public/amsfonts/cm/cmr9.pfb><D:/software/ctex/MiKTeX/fonts/type1/public/amsfonts/cm/cmsy10.pfb><D:/software/ctex/MiKTeX/fonts/type1/public/amsfonts/cm/cmsy5.pfb><D:/software/ctex/MiKTeX/fonts/type1/public/amsfonts/cm/cmsy7.pfb><D:/software/ctex/MiKTeX/fonts/type1/public/amsfonts/cm/cmsy8.pfb><D:/software/ctex/MiKTeX/fonts/type1/public/amsfonts/symbols/msam10.pfb><D:/software/ctex/MiKTeX/fonts/type1/public/amsfonts/symbols/msbm10.pfb><D:/software/ctex/MiKTeX/fonts/type1/public/cm-super/sfrm1000.pfb><D:/software/ctex/MiKTeX/fonts/type1/urw/times/utmb8a.pfb><D:/software/ctex/MiKTeX/fonts/type1/urw/times/utmbi8a.pfb><D:/software/ctex/MiKTeX/fonts/type1/urw/times/utmr8a.pfb><D:/software/ctex/MiKTeX/fonts/type1/urw/times/utmri8a.pfb>
|
||||
Output written on MarsRAG.pdf (14 pages, 381381 bytes).
|
||||
Output written on MarsRAG.pdf (14 pages, 381958 bytes).
|
||||
PDF statistics:
|
||||
175 PDF objects out of 1000 (max. 8388607)
|
||||
0 named destinations out of 1000 (max. 500000)
|
||||
|
||||
Binary file not shown.
Binary file not shown.
@@ -179,7 +179,7 @@ After the construction of the hyperbolic spatial hypergraph, the next step is to
|
||||
|
||||
1) Spatial Intent Extraction and Hyperedge Retrieval: Given a user query $q$, we first employ the LLM to extract spatial intent, including target entities, spatial constraints (footprint, region), temporal constraints ($L_s$ range, Sol range), and resolution preferences. These are denoted as query elements $\mathcal{K}_q$.
|
||||
|
||||
For each topic entity $e_s \in \mathcal{E}_q$ extracted from the query, we retrieve its incident spatial observation hyperedges $\mathcal{F}_{e_s} = \{f_{spa}^n \in \mathcal{F}_{spa} : e_s \in f_{spa}^n\}$ and derive pseudo-binary triples $(e_h, f_{spa}^n, e_t)$ for pairwise reasoning, following the approach of HyperRAG [18]:
|
||||
For each topic entity $e_s \in \mathcal{E}_q$ extracted from the query, we retrieve its incident spatial observation hyperedges $\mathcal{F}_{e_s} = \{f_{spa}^n \in \mathcal{F}_{spa} : e_s \in f_{spa}^n\}$ and derive pseudo-binary triples $(e_h, f_{spa}^n, e_t)$ for pairwise reasoning, following the approach of HyperRAG \cite{luo25hyperrag}:
|
||||
|
||||
\begin{equation}
|
||||
\label{equ:Spatial Intent Extraction and Hyperedge Retrieval}
|
||||
@@ -187,12 +187,11 @@ For each topic entity $e_s \in \mathcal{E}_q$ extracted from the query, we retri
|
||||
\end{equation}
|
||||
|
||||
2) Hyperbolic Spatial Encoding and Plausibility Scoring: For each candidate triple, we compute a spatiotemporal encoding that fuses semantic, structural, and physical-spatial signals:
|
||||
|
||||
\begin{equation}
|
||||
\label{equ:spatiotemporal encoding}
|
||||
\mathbf{x} = \left[\varphi(q) \| \varphi(e_h) \| \varphi(f_{spa}^n) \| \varphi(e_t) \| \delta(e_h, f_{spa}^n, e_t) \| \psi_{geo}(e_h, e_t)\right],
|
||||
\end{equation}
|
||||
where $\varphi$ denotes a text embedding model, $\delta$ denotes a structural proximity encoding adapted from SubGraphRAG [19] to operate on hyperedges, and $\psi_{geo}$ is the hyperbolic spatial encoding defined as:
|
||||
where $\varphi$ denotes a text embedding model, $\delta$ denotes a structural proximity encoding adapted from SubGraphRAG \cite{Li25SubGraphRAG} to operate on hyperedges, and $\psi_{geo}$ is the hyperbolic spatial encoding defined as:
|
||||
\begin{equation}
|
||||
\label{equ:hyperbolic spatial encoding}
|
||||
\psi_{geo}(e_h, e_t) = \left[d_K\left(\Phi(e_h), \Phi(e_t)\right), \; \Delta r(e_h, e_t), \; \cos\theta_{bearing}\right],
|
||||
@@ -203,23 +202,25 @@ where $d_K$ is the geodesic distance in $\mathbb{H}_K^d$ capturing physical prox
|
||||
\text{score}(e_h, f_{spa}^n, e_t) = f_\theta(\mathbf{x}) \in [0, 1].
|
||||
\end{equation}
|
||||
|
||||
Top-scored triples are retained and their tail entities form the frontier for next-hop expansion, following an adaptive search strategy with density-aware thresholding as in [18]. Specifically, we initialize with threshold $\tau_0 = 0.5$ and iteratively reduce by a decay factor $c = 0.1$ if the number of retrieved triples falls below a minimum acceptable count $M$, ensuring sufficient evidence coverage in sparse regions while preventing over-retrieval in dense regions.
|
||||
Top-scored triples are retained and their tail entities form the frontier for next-hop expansion, following an adaptive search strategy with density-aware thresholding as in \cite{luo25hyperrag}. Specifically, we initialize with threshold $\tau_0 = 0.5$ and iteratively reduce by a decay factor $c = 0.1$ if the number of retrieved triples falls below a minimum acceptable count $M$, ensuring sufficient evidence coverage in sparse regions while preventing over-retrieval in dense regions.
|
||||
|
||||
3) Spatial Outward Einstein Midpoint Aggregation: After retrieval, the selected multi-source evidence typically spans multiple resolutions. To aggregate these into a unified representation without losing fine-scale information, we introduce the Spatial Outward Einstein Midpoint (Spatial OEM). The motivation stems from a known failure mode: naively averaging hyperbolic embeddings collapses representations toward the origin, destroying the hierarchical structure encoded in radial depth [20].
|
||||
3) Spatial Outward Einstein Midpoint Aggregation: After retrieval, the selected multi-source evidence typically spans multiple resolutions. To aggregate these into a unified representation without losing fine-scale information, we introduce the Spatial Outward Einstein Midpoint (Spatial OEM). The motivation stems from a known failure mode: naively averaging hyperbolic embeddings collapses representations toward the origin, destroying the hierarchical structure encoded in radial depth \cite{madhu26hyprag}.
|
||||
|
||||
Given spatial observation hyperedge embeddings $\{\Phi(f_i)\}_{i=1}^n \subset \mathbb{H}_K^d$ with query-relevance weights $w_i$ and resolution-aware radial weighting $\phi_{res}(f_i) = r(\Phi(f_i))^p$:
|
||||
|
||||
$$\mathbf{m}_{K,p}^{Spa\text{-}OEM} = \Pi_K\left(\frac{\sum_{i=1}^{n} w_i \cdot \phi_{res}(f_i) \cdot \lambda_i \cdot \Phi(f_i)}{\sum_{i=1}^{n} w_i \cdot \phi_{res}(f_i) \cdot \lambda_i}\right)$$
|
||||
|
||||
\begin{equation}
|
||||
\label{equ:Spatial OEM}
|
||||
\mathbf{m}_{K,p}^{Spa\text{-}OEM} = \Pi_K\left(\frac{\sum_{i=1}^{n} w_i \cdot \phi_{res}(f_i) \cdot \lambda_i \cdot \Phi(f_i)}{\sum_{i=1}^{n} w_i \cdot \phi_{res}(f_i) \cdot \lambda_i}\right),
|
||||
\end{equation}
|
||||
where $\lambda_i = \Phi(f_i)_0$ is the Lorentz factor and $\Pi_K$ denotes reprojection onto $\mathbb{H}_K^d$, defined as $\Pi_K(\mathbf{v}) = \frac{\mathbf{v}}{\sqrt{K \langle \mathbf{v}, \mathbf{v} \rangle_L}}$ for $\mathbf{v}$ with $\langle \mathbf{v}, \mathbf{v} \rangle_L < 0$ and $v_0 > 0$.
|
||||
|
||||
**Theorem 1** (Spatial OEM Outward Bias). *For $p \geq 1$, the Spatial OEM satisfies:*
|
||||
Theorem~1 (Spatial OEM Outward Bias). For $p \geq 1$, the Spatial OEM satisfies:
|
||||
\begin{equation}
|
||||
\label{equ:Spatial OEM Outward Bias}
|
||||
r(\mathbf{m}_{K,p}^{Spa\text{-}OEM}) \geq r(\mathbf{m}_K^{Ein}),
|
||||
\end{equation}
|
||||
where $\mathbf{m}_K^{Ein}$ is the standard Einstein midpoint ($p = 0$).
|
||||
|
||||
$$r(\mathbf{m}_{K,p}^{Spa\text{-}OEM}) \geq r(\mathbf{m}_K^{Ein})$$
|
||||
|
||||
*where $\mathbf{m}_K^{Ein}$ is the standard Einstein midpoint ($p = 0$).*
|
||||
|
||||
*Proof.* The OEM weights $\tilde{w}_i \propto w_i \cdot r(\Phi(f_i))^{p+1}$ concentrate more mass on high-radius points than the Einstein weights $w_i \cdot r(\Phi(f_i))$. By the Chebyshev sum inequality applied to the co-monotonic sequences $a_i = r(\Phi(f_i))^{p+1}$ and $b_i = r(\Phi(f_i))$, the pre-projection time component satisfies $\tilde{v}_0 \geq \bar{r}_w$ (weighted mean radius). Since reprojection $\Pi_K$ preserves the ordering of time components, the result follows. $\square$
|
||||
Proof. The OEM weights $\tilde{w}_i \propto w_i \cdot r(\Phi(f_i))^{p+1}$ concentrate more mass on high-radius points than the Einstein weights $w_i \cdot r(\Phi(f_i))$. By the Chebyshev sum inequality applied to the co-monotonic sequences $a_i = r(\Phi(f_i))^{p+1}$ and $b_i = r(\Phi(f_i))$, the pre-projection time component satisfies $\tilde{v}_0 \geq \bar{r}_w$ (weighted mean radius). Since reprojection $\Pi_K$ preserves the ordering of time components, the result follows. $\square$
|
||||
|
||||
The outward bias guarantees that high-resolution observations dominate the aggregated representation. This is essential for planetary science retrieval: when a user queries a specific geological feature, the aggregated evidence should preserve the fine-scale observational details rather than being smoothed into a coarse-resolution summary.
|
||||
|
||||
@@ -227,28 +228,33 @@ The outward bias guarantees that high-resolution observations dominate the aggre
|
||||
|
||||
We define the multi-source spatial evidence retrieved in a single query as observation-grounded homologous data (Definition 4). Although targeting the same query object, these data often provide inconsistent factual statements due to differences in instrument principles, observation geometry, and acquisition epochs. Unlike MultiRAG's Multi-level Confidence Computing (MCC), which assumes that inconsistency indicates unreliability and employs mutual information entropy to filter conflicting nodes, we adopt a fundamentally different paradigm: Physics-Informed Conflict Triage (PICT), which classifies conflicts by their physical origin and applies differentiated processing strategies.
|
||||
|
||||
1) Cross-Source Interaction Entropy: The first stage detects conflicts by measuring the information-theoretic interaction effect when two sources are jointly presented to the LLM. Existing entropy-based conflict detection methods, such as TruthfulRAG [17], compare retrieval-augmented entropy against parametric-only entropy ($\Delta H_p = H(P_{aug}) - H(P_{param})$). However, this formulation is inapplicable to our setting where all knowledge is external observational data rather than LLM parametric knowledge. We instead propose cross-source interaction entropy that measures the mutual interference between two observation sources:
|
||||
|
||||
$$\mathcal{H}_{inter}(p_i, p_j \mid q) = H\left(P(\text{ans} \mid q, p_i \oplus p_j)\right) - \frac{1}{2}\left[H\left(P(\text{ans} \mid q, p_i)\right) + H\left(P(\text{ans} \mid q, p_j)\right)\right],$$
|
||||
1) Cross-Source Interaction Entropy: The first stage detects conflicts by measuring the information-theoretic interaction effect when two sources are jointly presented to the LLM. Existing entropy-based conflict detection methods, such as TruthfulRAG \cite{liu26truthfulrag}, compare retrieval-augmented entropy against parametric-only entropy ($\Delta H_p = H(P_{aug}) - H(P_{param})$). However, this formulation is inapplicable to our setting where all knowledge is external observational data rather than LLM parametric knowledge. We instead propose cross-source interaction entropy that measures the mutual interference between two observation sources:
|
||||
\begin{equation}
|
||||
\label{equ:interaction entropy}
|
||||
\mathcal{H}_{inter}(p_i, p_j \mid q) = H\left(P(\text{ans} \mid q, p_i \oplus p_j)\right) - \frac{1}{2}\left[H\left(P(\text{ans} \mid q, p_i)\right) + H\left(P(\text{ans} \mid q, p_j)\right)\right],
|
||||
\end{equation}
|
||||
where $H(\cdot)$ is the token-averaged entropy over top-$k$ candidate tokens:
|
||||
|
||||
$$H\left(P(\text{ans} \mid \text{context})\right) = -\frac{1}{|l|}\sum_{t=1}^{|l|}\sum_{i=1}^{k} pr_i^{(t)} \log_2 pr_i^{(t)}$$
|
||||
|
||||
\begin{equation}
|
||||
\label{equ:token-averaged entropy}
|
||||
H\left(P(\text{ans} \mid \text{context})\right) = -\frac{1}{|l|}\sum_{t=1}^{|l|}\sum_{i=1}^{k} pr_i^{(t)} \log_2 pr_i^{(t)},
|
||||
\end{equation}
|
||||
and $p_i \oplus p_j$ denotes the concatenation of both reasoning paths derived from sources $\mathcal{K}_i$ and $\mathcal{K}_j$ respectively. The interaction entropy admits a clear physical interpretation: positive values ($\mathcal{H}_{inter} > 0$, super-additive uncertainty) indicate that the two sources contradict each other, jointly creating more confusion than either alone; near-zero values indicate independence or consistency; negative values (sub-additive) indicate mutual complementarity where the sources reinforce each other.
|
||||
|
||||
Reasoning path pairs exhibiting interaction entropy exceeding a predefined threshold $\epsilon$ are classified as detected conflicts:
|
||||
|
||||
$$\mathcal{C}^{detected} = \{(\psi_i, \psi_j) \mid \mathcal{H}_{inter}(p_i, p_j \mid q) > \epsilon\}$$
|
||||
\begin{equation}
|
||||
\label{equ:conflict detection}
|
||||
\mathcal{C}^{detected} = \{(\psi_i, \psi_j) \mid \mathcal{H}_{inter}(p_i, p_j \mid q) > \epsilon\}.
|
||||
\end{equation}
|
||||
|
||||
2) Physics-Informed Conflict Classification: The second stage classifies each detected conflict by its physical origin. We introduce the central distinction of PICT:
|
||||
|
||||
**Definition 7. Explainable conflict and opaque conflict.** A pairwise conflict $(\psi_i, \psi_j) \in \mathcal{C}_{i,j}$ is *explainable* if there exists a physical bridging function $\mathcal{B}$ such that:
|
||||
Definition~7 (Explainable conflict and opaque conflict). A pairwise conflict $(\psi_i, \psi_j) \in \mathcal{C}_{i,j}$ is explainable if there exists a physical bridging function $\mathcal{B}$ such that:
|
||||
\begin{equation}
|
||||
\label{equ:explainable conflict}
|
||||
\mathcal{B}(\Omega_i, \Omega_j, \mathcal{M}_i, \mathcal{M}_j) \models \neg(\psi_i \bot \psi_j).
|
||||
\end{equation}
|
||||
|
||||
$$\mathcal{B}(\Omega_i, \Omega_j, \mathcal{M}_i, \mathcal{M}_j) \models \neg(\psi_i \bot \psi_j).$$
|
||||
|
||||
i.e., the apparent inconsistency is resolvable by accounting for observation constraint differences ($\Omega_i$, $\Omega_j$) and measurement model differences ($\mathcal{M}_i$, $\mathcal{M}_j$). Otherwise, the conflict is *opaque*.
|
||||
|
||||
Based on this distinction, we define four conflict categories, each with a differentiated processing strategy:
|
||||
i.e., the apparent inconsistency is resolvable by accounting for observation constraint differences ($\Omega_i$, $\Omega_j$) and measurement model differences ($\mathcal{M}_i$, $\mathcal{M}_j$). Otherwise, the conflict is opaque.
|
||||
|
||||
\begin{table}
|
||||
\renewcommand{\arraystretch}{1.3}
|
||||
@@ -256,7 +262,7 @@ Based on this distinction, we define four conflict categories, each with a diffe
|
||||
\label{table_conflict_triage}
|
||||
\vspace{-0.13in}
|
||||
\centering
|
||||
\begin{tabular}{|m{3cm}|m{3cm}|m{3cm}|}
|
||||
\begin{tabular}{|m{2.1cm}|m{2.8cm}|m{2.8cm}|}
|
||||
\hline
|
||||
\makecell[c]{\textbf{Category}} & \makecell[c]{\textbf{Condition}} & \makecell[c]{\textbf{Strategy}} \\
|
||||
\hline
|
||||
@@ -272,29 +278,40 @@ Based on this distinction, we define four conflict categories, each with a diffe
|
||||
\end{tabular}
|
||||
\end{table}
|
||||
|
||||
For each detected conflict, we construct a feature vector that fuses information-theoretic, physical, and neural signals:
|
||||
|
||||
$$\mathbf{z}_{conf} = \left[\mathcal{H}_{inter}, \; \|\Omega_i - \Omega_j\|, \; |\log(\ell_{res}^i / \ell_{res}^j)|, \; \Delta\mathcal{T}, \; \rho_{auth}(i,j), \; \mathbf{h}^{(l^*)}_{conf}\right]$$
|
||||
|
||||
Based on this distinction, we define four conflict categories, each with a differentiated processing strategy, as shown in Table~\ref{table_conflict_triage}. For each detected conflict, we construct a feature vector that fuses information-theoretic, physical, and neural signals:
|
||||
\begin{equation}
|
||||
\label{equ:conflict classification feature vector}
|
||||
\mathbf{z}_{conf} = \left[\mathcal{H}_{inter}, \; \|\Omega_i - \Omega_j\|, \; |\log(\ell_{res}^i / \ell_{res}^j)|, \; \Delta\mathcal{T}, \; \rho_{auth}(i,j), \; \mathbf{h}^{(l^*)}_{conf}\right],
|
||||
\end{equation}
|
||||
where $\|\Omega_i - \Omega_j\|$ is the observation geometry disparity, $|\log(\ell_{res}^i / \ell_{res}^j)|$ is the resolution ratio in log-scale, $\Delta\mathcal{T}$ is the temporal separation, $\rho_{auth}(i,j)$ is the authority disparity between sources, and $\mathbf{h}^{(l^*)}_{conf}$ is the LLM hidden state at the conflict encoding layer. The inclusion of $\mathbf{h}^{(l^*)}_{conf}$ is motivated by the finding that knowledge conflict signals concentrate in mid-to-late layers of LLMs and are linearly separable with > 93% AUC [21].
|
||||
|
||||
A lightweight classifier maps the feature vector to conflict type:
|
||||
|
||||
$$\hat{c} = \arg\max_{c \in \{noise, inst, scale, temp\}} P_\theta(c \mid \mathbf{z}_{conf})$$
|
||||
\begin{equation}
|
||||
\label{equ:conflict classification}
|
||||
\hat{c} = \arg\max_{c \in \{noise, inst, scale, temp\}} P_\theta(c \mid \mathbf{z}_{conf}).
|
||||
\end{equation}
|
||||
|
||||
Lemma~1 (Conflict Type Separability). The four conflict types are distinguished by orthogonal physical dimensions: $\|\Omega_i - \Omega_j\|$ separates instrument conflicts; $|\log(\ell_{res}^i / \ell_{res}^j)|$ separates scale conflicts; $\Delta\mathcal{T}$ separates temporal conflicts; $\rho_{auth}$ separates noise conflicts. Since these physical features are independent of and complementary to the hidden state features $\mathbf{h}^{(l^*)}_{conf}$ (which encode semantic inconsistency), the four conflict types are linearly separable in the augmented feature space $\mathbf{z}_{conf}$.
|
||||
|
||||
3) Conflict-Aware Confidence Recalibration: Based on the classification result, we recalibrate the node confidence. This is the key departure from MultiRAG's MCC, which uniformly penalizes inconsistency:
|
||||
|
||||
$$C_{triage}(v) = \begin{cases} C_{base}(v) & \text{if } v \notin \mathcal{C}^{detected} \\ \alpha \cdot C_{base}(v) + (1-\alpha) \cdot \eta & \text{if } \hat{c} = noise \\ C_{base}(v) + \beta \cdot \mathcal{H}_{inter}^{-1} & \text{if } \hat{c} \in \{inst, scale\} \\ C_{base}(v) \cdot \gamma(|\Delta\mathcal{T}|) & \text{if } \hat{c} = temp \end{cases}$$
|
||||
|
||||
\begin{equation}
|
||||
\label{equ:conflict classification}
|
||||
C_{triage}\left( v \right) =\begin{cases}
|
||||
C_{base}\left( v \right)& \text{if\,\,}v\ni \mathcal{C}^{detected}\\
|
||||
\alpha \cdot C_{base}\left( v \right) +\left( 1-\alpha \right) \cdot \eta& \text{if\,\,}\hat{c}=noise\\
|
||||
C_{base}\left( v \right) +\beta \cdot \mathcal{H}_{inter}^{-1}& \text{if\,\,}\hat{c}\in \{inst,scale\}\\
|
||||
C_{base}\left( v \right) \cdot \gamma \left( |\Delta \mathcal{T}| \right)& \text{if\,\,}\hat{c}=temp,\\
|
||||
\end{cases}
|
||||
\end{equation}
|
||||
where $C_{base}(v)$ is the baseline confidence computed via semantic similarity (analogous to the node consistency score in [14]), $\eta < 0$ is a penalty term for noise conflicts, $\beta > 0$ is a boost coefficient for scientifically explainable conflicts, and $\gamma(|\Delta\mathcal{T}|)$ is a time-decay weighting function that prioritizes recent observations while preserving temporal evolution signals. Specifically, $\gamma(|\Delta\mathcal{T}|) = 1 + \beta_{temp} \cdot \exp(-|\Delta\mathcal{T}| / \tau_{decay})$, where $\beta_{temp} > 0$ ensures $\gamma > 1$ for temporal contrasts with scientific significance.
|
||||
|
||||
**Theorem 2** (Anti-Over-Smoothing Guarantee). *Let $V_{sci} \subset V$ denote the set of nodes involved in explainable scientific conflicts ($\mathcal{C}^{inst} \cup \mathcal{C}^{scale} \cup \mathcal{C}^{temp}$). Under PICT with $\beta > 0$:*
|
||||
Theorem~2 (Anti-Over-Smoothing Guarantee). Let $V_{sci} \subset V$ denote the set of nodes involved in explainable scientific conflicts ($\mathcal{C}^{inst} \cup \mathcal{C}^{scale} \cup \mathcal{C}^{temp}$). Under PICT with $\beta > 0$:
|
||||
\begin{equation}
|
||||
\label{equ:Anti-Over-Smoothing Guarantee}
|
||||
C_{triage}(v) > C_{base}(v) \quad \forall v \in V_{sci}.
|
||||
\end{equation}
|
||||
|
||||
$$C_{triage}(v) > C_{base}(v) \quad \forall v \in V_{sci}$$
|
||||
|
||||
*Proof.* For $v \in \mathcal{C}^{inst} \cup \mathcal{C}^{scale}$: $C_{triage}(v) = C_{base}(v) + \beta \cdot \mathcal{H}_{inter}^{-1}$. Since $\beta > 0$ and $\mathcal{H}_{inter} > \epsilon > 0$ (by the detection threshold in Eq. 16), $\beta \cdot \mathcal{H}_{inter}^{-1} > 0$, thus $C_{triage}(v) > C_{base}(v)$. For $v \in \mathcal{C}^{temp}$: $\gamma(|\Delta\mathcal{T}|) > 1$ by construction (since $\beta_{temp} > 0$ and $\exp(\cdot) > 0$), thus $C_{triage}(v) = C_{base}(v) \cdot \gamma(|\Delta\mathcal{T}|) > C_{base}(v)$. $\square$
|
||||
Proof. For $v \in \mathcal{C}^{inst} \cup \mathcal{C}^{scale}$: $C_{triage}(v) = C_{base}(v) + \beta \cdot \mathcal{H}_{inter}^{-1}$. Since $\beta > 0$ and $\mathcal{H}_{inter} > \epsilon > 0$ (by the detection threshold in Eq. 16), $\beta \cdot \mathcal{H}_{inter}^{-1} > 0$, thus $C_{triage}(v) > C_{base}(v)$. For $v \in \mathcal{C}^{temp}$: $\gamma(|\Delta\mathcal{T}|) > 1$ by construction (since $\beta_{temp} > 0$ and $\exp(\cdot) > 0$), thus $C_{triage}(v) = C_{base}(v) \cdot \gamma(|\Delta\mathcal{T}|) > C_{base}(v)$. $\square$
|
||||
|
||||
This theorem provides a formal guarantee that scientifically valuable conflict nodes can never be suppressed below their baseline confidence by the triage mechanism, directly addressing the over-smoothing problem.
|
||||
|
||||
@@ -324,13 +341,13 @@ We propose the AreoRAG Prompting (ARP) algorithm for multi-source planetary spat
|
||||
\end{algorithmic}
|
||||
\end{algorithm}
|
||||
|
||||
Given a user query $q$, the LLM is first employed to extract entities, spatial constraints ($\mathcal{P}_{foot}$, region), and temporal constraints ($\mathcal{T}_{win}$, $L_s$ range), generating corresponding logical and spatial relationships. The observation data then undergoes multi-source spatial adapter parsing to derive normalized datasets (Eq. 4), followed by constructing a Hyperbolic Spatial Hypergraph via scale-aware Lorentz embedding and cross-reference-frame alignment (Eq. 6-8).
|
||||
Given a user query $q$, the LLM is first employed to extract entities, spatial constraints ($\mathcal{P}_{foot}$, region), and temporal constraints ($\mathcal{T}_{win}$, $L_s$ range), generating corresponding logical and spatial relationships. The observation data then undergoes multi-source spatial adapter parsing to derive normalized datasets (line 4), followed by constructing a Hyperbolic Spatial Hypergraph via scale-aware Lorentz embedding and cross-reference-frame alignment (lines 6-8).
|
||||
|
||||
Subsequently, spatiotemporal retrieval is performed using hyperbolic spatial encoding and MLP-based plausibility scoring (Eq. 10-12), with Spatial OEM aggregation (Eq. 13) to produce a unified cross-resolution representation. The cross-source interaction entropy mechanism (Eq. 14-16) then detects inter-source conflicts, after which each detected conflict is classified via the physics-informed feature vector (Eq. 18-19) and the node confidence is recalibrated accordingly (Eq. 20).
|
||||
Subsequently, spatiotemporal retrieval is performed using hyperbolic spatial encoding and MLP-based plausibility scoring (lines 10-12), with Spatial OEM aggregation (line 13) to produce a unified cross-resolution representation. The cross-source interaction entropy mechanism (lines 14-16) then detects inter-source conflicts, after which each detected conflict is classified via the physics-informed feature vector (lines 18-19) and the node confidence is recalibrated accordingly (line 20).
|
||||
|
||||
The final step constructs a differential context based on the triage result. For noise conflicts, the low-authority source is filtered, compatible with conventional conflict elimination. For instrument-inherent and scale-dependent conflicts, both sources are preserved with a physical bridging explanation $\mathcal{B}(\Omega_i, \Omega_j)$ appended to the context, enabling the LLM to reason about the physical origin of the disagreement. For temporal-evolution conflicts, a temporal ordering is constructed, allowing the LLM to trace the evolution of observations over time. All preserved evidence carries provenance metadata (DataID, source institution, instrument identity, observation timestamp in $L_s$) to ensure scientific traceability, analogous to the citation anchors in Perplexity-style retrieval systems.
|
||||
|
||||
It should be noted that the ARP algorithm constructs the HySH offline as a preprocessing step, while the PICT module operates online during each query. The HySH construction time is dominated by the LLM-based entity extraction (comparable to MultiRAG's MLG construction), while the online PICT overhead consists primarily of $|\mathcal{C}^{detected}|$ forward passes through the lightweight conflict classifier (Eq. 19), which is negligible compared to the LLM generation cost.
|
||||
It should be noted that the ARP algorithm constructs the HySH offline as a preprocessing step, while the PICT module operates online during each query. The HySH construction time is dominated by the LLM-based entity extraction (comparable to MultiRAG's MLG construction), while the online PICT overhead consists primarily of $|\mathcal{C}^{detected}|$ forward passes through the lightweight conflict classifier (line 19), which is negligible compared to the LLM generation cost.
|
||||
|
||||
\section{Experiments}
|
||||
This section conducts experiments and performance analysis on the Hyperbolic Spatial Hypergraph (HySH) construction and the Physics-Informed Conflict Triage (PICT) modules. Baseline methods are compared with SOTA multi-source retrieval, graph-based RAG, and conflict-resolution methods. Extensive experiments are conducted to assess the robustness and efficiency of AreoRAG, which aims to answer the following questions.
|
||||
|
||||
@@ -404,3 +404,15 @@
|
||||
journal={arXiv preprint arXiv:2602.14518},
|
||||
year={2026}
|
||||
}
|
||||
|
||||
@inproceedings{Li25SubGraphRAG,
|
||||
author = {Mufei Li and
|
||||
Siqi Miao and
|
||||
Pan Li},
|
||||
title = {Simple is Effective: The Roles of Graphs and Large Language Models
|
||||
in Knowledge-Graph-Based Retrieval-Augmented Generation},
|
||||
booktitle = {The Thirteenth International Conference on Learning Representations,
|
||||
{ICLR} 2025, Singapore, April 24-28, 2025},
|
||||
publisher = {OpenReview.net},
|
||||
year = {2025}
|
||||
}
|
||||
Reference in New Issue
Block a user