Web This site Trusted
30 result(s) for “okapi bm25 site terms com pp site github com site going in site race builder tls site:arxiv.org” of 37 matched · 700 ms
Scope: Nishi’s own index (our crawl + Common Crawl) — not the whole live web. Some sites block all automated crawlers (anti-bot walls), so their pages may be absent here even though we never filter lawful content.
Freshness: no result on this page carries a fetch time yet (indexed before the fetch epoch was stored beside the doc)
The query asks the model to recall the topic of an earlier conversation about Tesla; the gold answer is anchored in one specific session about Pooja’s dig site
from the top result below
https://arxiv.org/html/2608.02613v1
7 Extrapolation across readers for cache-replay backends
TTFT rows in Table 3
https://arxiv.org/html/2608.03048v1
com/JetAstra/PI-Mem
Introduction
The ability to reason over long contexts is increasingly important for large language models (LLMs), supporting applications such as long-document question answering (Gemini Team 2025; Yang et al
https://arxiv.org/html/2501.13956v1
com
Abstract
We introduce Zep, a novel memory layer service for AI agents that outperforms the current state-of-the-art system, MemGPT, in the Deep Memory Retrieval (DMR) benchmark
https://arxiv.org/html/2407.16741v3
com/All-Hands-AI/OpenHands
Slack http://bit
https://arxiv.org/list/cs.AI/new
In practice, many field descriptions remain ambiguous or incomplete, as much of the essential context (e
https://arxiv.org/pdf/2407.02510
SYQ8+TD@uWśdt XPQiXWb{3R kC]:ԔSf9g~j8: ɓHicȲ ]U R[`bN'dINB4"vA"ѣv\E= PDқ*Mgyz(3 v-|$NewX$"Hɔ+4W c%\
https://arxiv.org/pdf/2407.02402
߯jD岻fc;Z̫MfG} q]/ޭmޯo⣩0Z^x]fkn{E+{*ʧypg6;5PVpH8$hmڢ*߄zR:")3qXysO'H)-"}[˺s 3 4{pYdrK+ a }ѫW{ Fvm7344AGc
https://arxiv.org/src/2006.02230
OP;hUA sInRFze\k"oV(Evi hmSJ t[WH D]&j 쵘 ^A*ُ52QPb zZU)6#/ nr 1IdawxSWeШw ,pla|@[Q§u;/;kR$OnBϵ6"r
https://arxiv.org/pdf/2407.00225
-scale, Independent and Comprehensive study of the power of LLMs for test case generationWendkûuni C. OuédraogoKader KaboréYinghua LiHaoye TianAnil KoyuncuJacques KleinDavid LoTegawendé F. Bissyandéhttp://creativecommons.org/licenses
https://arxiv.org/pdf/2608.04008
6>Ȍ6= RBmLLXƇM_ |VNe]V[Rª{5X68$T`="03[R/u C*JsI)u8WqMI|WG0hZ5+ާl* pair 3z } BxJ ߣۡjy ŃE"eSPL0 }O;ﮍk;_E 滳6") sr\#UxtQ 2~'wgrxW]pp*c )>VNbQW'Z]
https://arxiv.org/pdf/2608.03118
Zz|PG-T*1P8Y v k-'Nğ`PM $&] L'|* p7k7mE7nry09U=PP#'#ބv2Z$t;Ʀlr5
https://arxiv.org/src/2608.03883
lއxG&JWXԴ&[v @V[uԇF7vz%N` pP \>$kb {K/05 U0[|ʋX cc S-bQEAE
https://arxiv.org/src/2006.00508
6t[Þ9{ʞ{Wwb {ޱ #;X/ŭIf30q6g d ]3,dE=YRvVl>H:OAib vĆlĎ٘Sv ;!"H )5Naxzj 8џ7 4 y jHx:_yf!~Noi2VoZ
https://arxiv.org/pdf/2608.03411
{~l F )=PH# ӑHton> stream DUD: Decoupled Update Dynamics for Reliable Uncertainty Quantification in Large Language ModelsYixin BuRunze XiaGuanyun ZouYupeng JiHaodong LiuPiji Lihttp://creativecommons
https://arxiv.org/src/2005.14165
0鮪GeZ ON!N\磻 =9'Ebkc>iBh'Xfܺ7:{w 1ÓORq/7uuZuguuoIx[Knv~;oNNL!:.9m7EB xBc~[*
https://arxiv.org/src/2006.02085
@z/|h LT;QUHqK)S½$iNjMUbiI
https://arxiv.org/pdf/2006.01402
G_ ΄ _a~29 0 LO ӁIN2
https://arxiv.org/pdf/2006.04122
/Width 614 >> stream x XkǏ=D!D6"ZT$E%BEgQ)tJ{hU(J+!V) D~s)Ie_5ͼ P( j BP(D& BP iӦAP( E# ȄBP(hDP( BP("BP(D& %%X B~; ߿[^
https://arxiv.org/pdf/2608.02666
'd$ WU )]Wu}~1J Д&Y{S.i臿Exiy=U%]REYy[tE.zK]::( .Yy9_b\_odGva-KF){:^>^ou_^GmϟooޤS9TQNR2)ۢ\[NUtE:dM&UYb-@u%
https://arxiv.org/pdf/2608.02935
0 rFBLS^C#)^ku7qy dZ1% rF>2tK0(OB{յ;7] GJӽpM Gpp-dR-|qd
https://arxiv.org/abs/2608.03883
All submitted systems follow a staged retrieval design in which BM25 retrieves candidates at scale and semantic or LLM rerankers refine the final rankings
https://arxiv.org/list/cs.CL/new
LG)
Half a million cuneiform clay tablets survive in museums worldwide, yet modern users can neither read nor write in the world's oldest writing system, leaving a 4,000-year cultural barrier that existing NLP tools have only partially addressed
https://arxiv.org/html/2508.20108v2
How can we address distribution shifts in stock price data to improve stock price prediction accuracy
https://arxiv.org/abs/2104.08663
Benchmark for Zero-shot Evaluation of Information Retrieval Models, by Nandan Thakur and 4 other authors
View PDF HTML (experimental)
Abstract:Existing neural information retrieval (IR) models have often been studied in homogeneous and narrow settings, which has considerably limited insights into their out-of
https://arxiv.org/abs/2608.03860
The pipeline combines sentence-window chunking, BM25, BGE-M3 dense retrieval, reciprocal rank fusion, optional cross-encoder reranking, and grounded answer generation
https://arxiv.org/list/cs.IR/recent
Skip to main content
System maintenance August 4th and 5th Learn more ×
Search Submit Donate Log in
Search arXiv
Press Enter to search · Advanced search
Information Retrieval
Authors and titles for recent submissions
Wed, 5 Aug 2026
https://arxiv.org/list/cs.IR/new
In a live A/B test on Shopee Homepage Search, it increases GMV per user by 1
https://arxiv.org/pdf/2006.00441
dqʒKYd[_!h y̙ѐ BE$Q$ŷ7K2蒌cOJR"` B)C hMu & ~6["FNK3jV8l!t6l8J6ڏC7~_hCB 6 湘)> stream xq0- n,㡝A/d}u"30P6-
https://arxiv.org/pdf/2310.19147
1m in >~4ͫW-*-sFg%y%|ҴGZbclؐ\
https://arxiv.org/pdf/2608.02942
+e,L}Ëuh{ǀHJ'>N>NA-z*ky nx ZZ{I3qF_z MJӠPp