ISQA：面向科学摘要的信息性事实性反馈
ISQA: Informative Factuality Feedback for Scientific Summarization
AI总结：
提出ISQA方法，利用包含正负面信息的模型生成反馈对摘要进行迭代优化，要求智能体强化已验证陈述并修正错误陈述，显著提升了多种开源LLM在科学摘要任务上的事实性。
摘要：
我们提出基于信息性科学问答（ISQA）反馈的迭代事实性优化，这是一种遵循人类学习理论的方法，采用包含正面和负面信息的模型生成反馈。通过对摘要进行迭代优化，它探究陈述背后的潜在逻辑，以增强科学摘要的事实性。ISQA以细粒度方式实现这一点，要求摘要智能体在正面反馈中强化已验证的陈述，并在负面反馈中修正错误的陈述。我们的研究结果表明，ISQA反馈机制在多个科学数据集上的评估中，显著提升了多种开源LLM在摘要任务上的事实性。
英文摘要：
We propose Iterative Facuality Refining on Informative Scientific Question-Answering (ISQA) feedback\footnote{Code is available at \url{https://github.com/lizekai-richard/isqa}}, a method following human learning theories that employs model-generated feedback consisting of both positive and negative information. Through iterative refining of summaries, it probes for the underlying rationale of statements to enhance the factuality of scientific summarization. ISQA does this in a fine-grained manner by asking a summarization agent to reinforce validated statements in positive feedback and fix incorrect ones in negative feedback. Our findings demonstrate that the ISQA feedback mechanism significantly improves the factuality of various open-source LLMs on the summarization task, as evaluated across multiple scientific datasets.
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。
