Web This site Trusted
20 result(s) for “okapi bm25 site terms com pp site github com site www minor an site simha ca site:arxiv.org” · 1105 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
We evaluate five open-weight readers with Vanilla context, BM25-RAG, Oracle retrieval, Memobase, and MemSearch as memory backends
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/html/2407.04503v4
Molinaro Inria, Flowers team, Université de Bordeaux, France Department of Psychology, University of California, Berkeley, Berkeley, CA, USA Maxime Derex Institute for Advanced Study in Toulouse, Toulouse, France Pierre-Yves Oudeyer Inria, Flowers team, Université de Bordeaux, France Clément Moulin-Frier Inria
https://arxiv.org/list/cs.AI/new
CL)
Recent studies have identified an ``Artificial Hivemind'' effect in Large Language Models (LLMs) causing models to converge on a narrow, homogenized consensus even for open questions
https://arxiv.org/list/math/new
The proof proceeds by introducing an auxiliary graph associated with the set $X$ and reducing the problem to bounding the largest eigenvalue of its adjacency matrix
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/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/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/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
LG)
As lifelong learning agents accumulate lifelong growing skill banks, retrieving the correct skill becomes an increasingly important bottleneck
https://arxiv.org/list/cs.CL/new
NE)
Formulating an optimization problem strongly affects the quality of the final solution, yet good formulations usually require substantial expertise
https://arxiv.org/html/2609.03371v1
Report GitHub Issue
Description:
arXiv is now an independent nonprofit
https://arxiv.org/html/2608.02975v1
com
Abstract
Large language models (LLMs) have demonstrated impressive performance in MQM-based translation quality (TQ) evaluation, and recent advances in large reasoning models (LRMs) promise even greater improvements
https://arxiv.org/list/astro-ph/2008-04
References updated and some minor changes
https://arxiv.org/list/astro-ph.SR/new
We report the identification of an unambiguous Galactic example in a short-period ($P=5
https://arxiv.org/list/gr-qc/new
charged Morris-Thorne-type traversable wormholes by solving the Einstein field equations with an anisotropic fluid as the energy-momentum tensor and analysing the resulting solutions
https://arxiv.org/list/cs.CR/new
We show that a natural pairwise-correlation extension to three or more stages is invalid because it gives a lower rather than an upper bound, and derive a valid spanning-tree alternative
https://arxiv.org/list/quant-ph/new
In this work, we initiate the study of a fundamental theorem for matrix product locally purifiable density operators (LPDOs) and focus on sequentially generated LPDOs (sLPDOs), a broad subclass admitting an interpretation in terms of successive applications of quantum channels on an initial state