Web This site Trusted
30 result(s) for “okapi bm25 site terms com pp site github com site answers apache org site:arxiv.org” of 37 matched · 977 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: newest result fetched 24 d ago · median age of these results 24 d · 1 of 30 carry a fetch time
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
We evaluate five open-weight readers with Vanilla context, BM25-RAG, Oracle retrieval, Memobase, and MemSearch as memory backends
https://arxiv.org/html/2510.03215v2
Report GitHub Issue
Description:
arXiv is now an independent nonprofit
https://arxiv.org/list/cs.AI/new
Research artifact available under the Apache-2
https://arxiv.org/html/2608.01366v2
org perpetual non-exclusive license
arXiv:2608
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/2608.00458v1
org perpetual non-exclusive license
arXiv:2608
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.CL/new
We evaluate five open-weight readers with Vanilla context, BM25-RAG, Oracle retrieval, Memobase, and MemSearch as memory backends
https://arxiv.org/html/2608.03545v1
org perpetual non-exclusive license
arXiv:2608
https://arxiv.org/html/2608.03141v1
org perpetual non-exclusive license
arXiv:2608
https://arxiv.org/html/2608.01085v1
org perpetual non-exclusive license
arXiv:2608
https://arxiv.org/html/2402.03300v3
com/deepseek-ai/DeepSeek-Math
Abstract
Mathematical reasoning poses a significant challenge for language models due to its complex and structured nature
https://arxiv.org/html/2608.03703v1
begun on July 20, 2026; the present version is dated August 4, 2026. Claude Opus 5 and Fable 5 provided research assistance throughout, spanning code development, data construction and empirical analysis, and the drafting of the manuscript.
https://arxiv.org/html/2608.02966v1
In conclusion, we show that incorrect answers carry distinct and useful measurement information rather than representing equivalent mistakes
https://arxiv.org/html/2608.03372v1
org GitHub
sourcecontextcandidatememoryalign claimscontent-word overlapseven checkspolarity ⋅\cdot condition ⋅\cdot temporalhedge ⋅\cdot attributionbrittle ⋅\cdot truncatedflagsevidence + citationverdict policyhard-codedpasspass_w_flagsrewriterejectuncheckablenever a passwitness (optional)one sentence, one
https://arxiv.org/html/2607.29281v2
Providing answers to policymakers, that is, producing policy recommendations on a given set of interventions of interest, requires making design choices along at least three dimensions
https://arxiv.org/html/2407.03956v3
This system tackles the complex puzzle-solving task by breaking down the problem into smaller, manageable parts, generating SMT (Satisfiability Modulo Theories) code to solve them with a theorem prover, and using feedback between the agents to repeatedly improve their answers
https://arxiv.org/html/2608.02621v1
com
Abstract
Legal benchmarks typically score final answers even when models also state legal authority
https://arxiv.org/html/2608.03411v1
com
Abstract
Accurate Uncertainty Quantification (UQ) is critical for reliable deployment of Large Language Models (LLMs), yet traditional probability-based metrics often fail to capture the model’s true epistemic state
https://arxiv.org/html/2410.05779v3
com Both Chao Huang and Yanhua Yu are corresponding authors
https://arxiv.org/html/2608.02665v1
9 pp, with bootstrap 95% CIs excluding zero for all five models, and 5–13% of seeds safe on canonical are unsafe under some reformulation—above a zero stochasticity floor (canonical resampled five times at temperature 0 gives 0/370 new exposures)
https://arxiv.org/html/2608.02625v1
Despite showing early promise, especially in terms of efficiency, DLMs face a fundamental challenge when applied to language generation: DLMs are by design inherently bidirectional
https://arxiv.org/html/2608.03573v1
org perpetual non-exclusive license
arXiv:2608
https://arxiv.org/list/cs.IR/recent
IR)
Tue, 4 Aug 2026 (showing first 34 of 45 entries )
[17] arXiv:2608
https://arxiv.org/abs/2608.03883
Our systems combine sparse BM25 retrieval, evidence-aware rescoring for self-referential symptom reports, embedding-based reranking, query-prototype expansion, and LLM-based reranking
https://arxiv.org/abs/2104.08663
Our results show BM25 is a robust baseline and re-ranking and late-interaction-based models on average achieve the best zero-shot performances, however, at high computational costs
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/html/2608.02617v1
Safe answers therefore require conservative behavior under ambiguity, calibrated uncertainty, and appropriate context-seeking
https://arxiv.org/html/2608.03044v1
Language Models for Opinion Simulation
Report GitHub Issue
×
Title:
Content selection saved. Describe the issue below:
Description:
Submit without GitHub Submit in GitHub
arXiv is now an independent nonprofit! Learn more ×
Back to