SYNFAC-EDIT: Synthetic Imitation Edit Feedback for Factual Alignment in Clinical Summarization

arXiv:2402.13919v1 Announce Type: new
Abstract: Large Language Models (LLMs) such as GPT and Llama have demonstrated significant achievements in summarization tasks but struggle with factual inaccuracies, a critical issue in clinical NLP applications where errors could lead to serious consequences. To counter the high costs and limited availability of expert-annotated data for factual alignment, this study introduces an innovative pipeline that utilizes GPT-3.5 and GPT-4 to generate high-quality feedback aimed at enhancing factual consistency in clinical note summarization. Our research …

abstract alignment applications arxiv availability clinical consequences costs cs.ai cs.cl edit errors feedback gpt issue language language models large language large language models llama llms nlp struggle summarization synthetic tasks type