NishiSearch

Web This site Trusted

12 result(s) for “okapi bm25 site terms com pp site hotchips pp site vi do union it site en site:arxiv.org” · 1194 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

Report GitHub Issue

https://arxiv.org/html/2608.02613v1
Instead, it falls on local, personal agents to effectively and safely maintain/utilize such dense person-person (PP) and person-agent (PA) interaction histories

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

Report GitHub Issue

https://arxiv.org/html/2608.03048v1
6 million tokens and find that it outperforms the recurrent-memory baseline by +6

[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

Computation and Language

https://arxiv.org/list/cs.CL/new
2 pp, exceeding MemSearch reader scaling (+10

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

Information Retrieval

https://arxiv.org/list/cs.IR/new
To handle it, KGD assigns them to separate parameter sets: a refreshable encoder owns behavioral knowledge, while a task learner reads contextualized encoder states through read-only cross-attention and writes task-specific geometry through Anchored Calibration Residual (ACR) orthogonal to the pretrained embedding

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)

1 Introduction

https://arxiv.org/html/2407.16741v3
edu Abstract Software is one of the most powerful tools that we humans have at our disposal; it allows a skilled programmer to interact with the world in complex and profound ways

Artificial Intelligence

https://arxiv.org/list/cs.AI/new
Extending the pattern-generation paradigm of Neural Cellular Automata (NCA), it navigates the degenerate Boolean search space to satisfy a computational task, rather than regenerating a fixed target state