Using contradictions improves question answering systems
원문 초록
This work examines the use of contradiction in natural language inference (NLI) for question answering (QA). Typically, NLI systems help answer questions by determining if a potential answer is \emph{entailed} (supported) by some background context. But is it useful to also determine if an answer contradicts the context? We test this in two settings, multiple choice and extractive QA, and find that systems that incorporate contradiction can do slightly better than entailment-only systems on certain datasets. However, the best performances come from using contradiction, entailment, and QA model confidence scores together. This has implications for the deployment of QA systems in domains such as medicine and science where safety is an issue.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Training-free LLM Merging for Multi-task Learning
Drop Dropout on Single-Epoch Language Model Pretraining
VAU-R1: Advancing Video Anomaly Understanding via Reinforcement Fine-Tuning
How Far Can Off-the-Shelf Multimodal Large Language Models Go in Online Episodic Memory Question Answering?
WikiMixQA: A Multimodal Benchmark for Question Answering over Tables and Charts
Thunder-NUBench: A Benchmark for LLMs' Sentence-Level Negation Understanding
토론
이 논문과 연결된 포럼 글이 아직 없습니다.