Logic Haystacks: Probing LLMs Long-Context Logical Reasoning (Without Easily Identifiable Unrelated Padding)
원문 초록
Large language models demonstrate promising long context processing capabilities, with recent models touting context windows close to one million tokens. However, the evaluations supporting these claims often involve simple retrieval tasks or synthetic tasks padded with irrelevant text, which the models may easily detect and discard. In this work, we generate lengthy simplified English text with first-order logic representations spanning up to 2048 clauses (around 25k GPT-4 tokens). We formulate an evaluation task with evidence retrieval for contradiction detection. The long, homogeneous text is filled with distractors that are both hard to distinguish from relevant evidences and provably not interfering with them. Our evaluation of evidence retrieval shows that the effective context window is much smaller with realistic distractors, already crumbling at 128 clauses.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Climate Finance Bench
From Roots to Rewards: Dynamic Tree Reasoning with RL
Developing Visual Augmented Q&A System using Scalable Vision Embedding Retrieval & Late Interaction Re-ranker
Seq vs Seq: An Open Suite of Paired Encoders and Decoders
Kodezi Chronos: A Debugging-First Language Model for Repository-Scale, Memory-Driven Code Understanding
RadiomicsRetrieval: A Customizable Framework for Medical Image Retrieval Using Radiomics Features
토론
이 논문과 연결된 포럼 글이 아직 없습니다.