ACL-Verbatim: hallucination-free question answering for research
Two new research papers address the critical issue of AI hallucinations in different domains. One paper introduces ACL-Verbatim, an extractive question-answering system designed to provide hallucination-free answers from research papers by mapping queries to verbatim text spans. The other paper, VIHD, proposes a visual intervention-based method for detecting hallucinations in medical visual question-answering models by analyzing cross-modal dependencies between text and visual tokens. AI
IMPACT These papers offer new techniques to improve the reliability of AI systems in research and medical applications, reducing risks associated with inaccurate information.