Context Length Alone Hurts LLM Performance Despite Perfect Retrieval
Yufeng Du, Minyang Tian, Srikanth Ronanki, Subendhu Rongali, Sravan Bodapati, Aram Galstyan, Azton Wells, Roy Schwartz, E. A. Huerta, Hao Peng
Abstract
Yufeng Du, Minyang Tian, Srikanth Ronanki, Subendhu Rongali, Sravan Babu Bodapati, Aram Galstyan, Azton Wells, Roy Schwartz, Eliu A Huerta, Hao Peng. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.
Topics & Concepts
Context (archaeology)Computer scienceArtificial intelligenceAssociation (psychology)Set (abstract data type)Information retrievalPsychologyEpistemologySelection (genetic algorithm)AlgorithmTopic ModelingNatural Language Processing TechniquesText Readability and Simplification