基于直接偏好优化的编码器-解码器模型临床阅读理解
Clinical Reading Comprehension with Encoder-Decoder Models Enhanced by Direct Preference Optimization
AI总结：
本研究将编码器-解码器模型与直接偏好优化结合，在RadQA放射学问答任务上提升12-15个F1点，首次证明DPO方法无需人工输入即可适用于阅读理解。
摘要：
对临床文本的抽取式问答是应对医院中产生的大量临床文本的关键需求。虽然编码器模型（如BERT）在此阅读理解任务中一直很流行，但近期编码器-解码器模型（如T5）正在兴起。同时，也出现了偏好优化技术，用于将仅解码器的大型语言模型与人类偏好对齐。在本文中，我们将编码器-解码器模型与直接偏好优化（DPO）方法相结合，在RadQA放射学问答任务上相较于先前最先进水平提升了12-15个F1分数点。据我们所知，这项工作首次表明DPO方法通过新颖的启发式方法生成无需人工输入的偏好数据，同样适用于阅读理解任务。
英文摘要：
Extractive question answering over clinical text is a crucial need to help deal with the deluge of clinical text generated in hospitals. While encoder models (e.g., BERT) have been popular for this reading comprehension task, recently encoder-decoder models (e.g., T5) are on the rise. There is also the emergence of preference optimization techniques to align decoder-only LLMs with human preferences. In this paper, we combine encoder-decoder models with the direct preference optimization (DPO) method to improve over prior state of the art for the RadQA radiology question answering task by 12-15 F1 points. To the best of our knowledge, this effort is the first to show that DPO method also works for reading comprehension via novel heuristics to generate preference data without human inputs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
