The first survey on Attention Sink in Transformers structures the literature around fundamental utilization, mechanistic interpretation, and strategic mitigation.
Lost in the middle: An emergent property from information retrieval demands in LLMs
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
SDSR places human metadata at file primacy and combines it with prompt routing rules to reach 100% primary category accuracy on a 119-category benchmark, far above the 65% no-guidance baseline.
Entity-based chunk filtering reduces RAG vector index size by 25-36% with retrieval quality near baseline levels.
Proposes treating LLMs as stochastic systems for student experimentation in statistics courses using Veridical Data Science and PCS principles, with four example activities across educational levels.
citing papers explorer
-
Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation
The first survey on Attention Sink in Transformers structures the literature around fundamental utilization, mechanistic interpretation, and strategic mitigation.
-
Self-Describing Structured Data with Dual-Layer Guidance: A Lightweight Alternative to RAG for Precision Retrieval in Large-Scale LLM Knowledge Navigation
SDSR places human metadata at file primacy and combines it with prompt routing rules to reach 100% primary category accuracy on a 119-category benchmark, far above the 65% no-guidance baseline.
-
Reducing Redundancy in Retrieval-Augmented Generation through Chunk Filtering
Entity-based chunk filtering reduces RAG vector index size by 25-36% with retrieval quality near baseline levels.
-
Probing the Stochastic Machine: Engaging with LLMs in Statistics Curricula Through Veridical Data Science
Proposes treating LLMs as stochastic systems for student experimentation in statistics courses using Veridical Data Science and PCS principles, with four example activities across educational levels.