Web This site Trusted
11 result(s) for “okapi bm25 site www eyespy cy site may may cy site dspace can cy site lord site:arxiv.org” · 574 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)
CY)
We show that knowledge distillation (KD) in small instruction-tuned language models has asymmetric effects on bias, and that measuring them correctly requires accounting for where refusal mass moves and what the parser can legitimately score
from the top result below
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/list/cs.AI/new
We demonstrate that it can self-assemble functional circuits from scratch and rapidly re-route logic around permanent, previously unseen hardware faults
https://arxiv.org/html/2501.13956v1
2 Knowledge Graph Construction
2.1 Episodes
2.2 Semantic Entities and Facts
2.2.1 Entities
2.2.2 Facts
2.2.3 Temporal Extraction and Edge Invalidation
2.3 Communities
3 Memory Retrieval
3.1 Search
3.2 Reranker
4 Experiments
4.1 Choice
https://arxiv.org/html/2608.03048v1
The read step processes all chunks in parallel, with each chunk-level read conditioned on the same global memory, thereby avoiding sequential memory overwrites that may discard earlier evidence and reducing inference latency through parallel chunk processing
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/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
02048 [pdf, html, other]
Title: SmartGR: Hierarchy and Beam-Aware Knowledge Distillation for Generative Recommendation
Ziheng Zhang, Yu Cui, Bohao Wang, Yong He, Chao Yu, Chuan Yuan, Wujie Sun, Can Wa
https://arxiv.org/list/cs.IR/new
For what to learn, conventional next-token prediction treats adjacency as dependency and may encode spurious transitions across unrelated sessions
https://arxiv.org/html/2407.16741v3
In particular, AI agents, systems that can perceive and act upon the external environment, have recently received ever-increasing research focus