NishiSearch

Web This site Trusted

30 result(s) for “okapi bm25 site terms com pp site github com site answers apache org site risk com site:arxiv.org” of 37 matched · 975 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 25 d ago · median age of these results 25 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

Report GitHub Issue

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

Artificial Intelligence

https://arxiv.org/list/cs.AI/new
Research artifact available under the Apache-2

Computation and Language

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

Report GitHub Issue

https://arxiv.org/html/2510.03215v2
Report GitHub Issue Description: arXiv is now an independent nonprofit

When Collaboration Becomes a Trigger:Collective Evidence-Threshold

https://arxiv.org/html/2608.01085v1
org perpetual non-exclusive license arXiv:2608

Producing Policy Recommendations: from Statistical Decision Theory to

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

Preying on Leveraged ETFsPreliminary and incomplete. This project was

https://arxiv.org/html/2608.03703v1
8 Dealer models, risk aversion, and neighboring structures D Empirical Extensions D

Report GitHub Issue

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

1 Introduction

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

1 Introduction

https://arxiv.org/html/2407.16741v3
com/All-Hands-AI/OpenHands Slack http://bit

Preferred, Not Safer: Pairwise Preference Is a Poor Proxy for Clinical

https://arxiv.org/html/2608.02617v1
Our analysis therefore treats evaluation as the object of study: we quantify preference–rubric alignment, report clinically meaningful failure rates (percentages of answers deemed objectively harmful or inaccurate by clinicians), and show that risk can concentrate in particular specialties even when global summaries

Every Wrong Answer Counts: Option-Level Psychometrics for LLM Multiple

https://arxiv.org/html/2608.02966v1
In conclusion, we show that incorrect answers carry distinct and useful measurement information rather than representing equivalent mistakes

Report GitHub Issue

https://arxiv.org/html/2608.00458v1
org perpetual non-exclusive license arXiv:2608

Report GitHub Issue

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

Asking Questions the Right Way: A Multi-Agent Conversational System for

https://arxiv.org/html/2608.01366v2
com Affiliation: Department of Design and Manufacturing, Indian Institute of Science (IISc) , Bangalore , India , Srinidhi Ranjini Girish email: srinidhirgirish@gmail

Report GitHub Issue

https://arxiv.org/html/2608.03545v1
org perpetual non-exclusive license arXiv:2608

Geometric Cross-Modal Token Selection for Latency-Constrained Multimodal

https://arxiv.org/html/2608.03141v1
org perpetual non-exclusive license arXiv:2608

Solving Zebra Puzzles Using Constraint-Guided Multi-Agent Systems

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

1 Introduction

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

Computer Vision and Pattern Recognition

https://arxiv.org/list/cs.CV/new
40, mean confidence on incorrect answers ranges from 0

Mathematics

https://arxiv.org/list/math/new
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 Mathematics New submissions Cross-lists Replacements See recent articles Showing

Information Retrieval

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

[2608.03883] DS@GT-ARC at eRisk 2026 Task 3: Sparse, Semantic, and LLM

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

[2104.08663] BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of

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

[2608.03860] SciRet: A Compute-Aware Empirical Study of Retrieval and

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

Single Canonical Prompts Underestimate LLM Safety’s Surface-Form

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)

Information Retrieval

https://arxiv.org/list/cs.IR/new
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 New submissions Cross-lists Replacements See recent

Knowing the Form, Not the Function: Automatically Auditing

https://arxiv.org/html/2608.02621v1
com Abstract Legal benchmarks typically score final answers even when models also state legal authority

Emulate or Estimate? The Divergent Strengths of Base and Post-Trained

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

Beyond Accuracy: A Multidimensional Evaluation of Statistical Reasoning

https://arxiv.org/html/2608.03038v1
in Large Language Models 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 arXiv Why HTML