面向知识增强零样本问答的证据聚焦型事实摘要
Evidence-Focused Fact Summarization for Knowledge-Augmented Zero-Shot Question Answering
AI总结：
针对知识图谱文本化存在的证据密度低、清晰度差的问题，提出EFSum证据聚焦型事实摘要框架，经蒸馏和偏好对齐优化开源大模型为摘要器，可提升大模型零样本问答性能，同时保证摘要有用性与忠实性。
摘要：
近期研究已探索利用知识图谱（Knowledge Graphs，KGs）提升大语言模型（Large Language Models，LLMs）的问答（Question Answering，QA）性能，但结构化KG的文本化仍具挑战。现有方法如三元组形式或三元组事实的自由文本转换，存在若干问题：包括因实体或关系重复导致的证据密度下降，以及因无法突出关键证据导致的证据清晰度降低。为解决这些问题，我们提出EFSum——一种用于知识增强LLM问答提升的证据聚焦型事实摘要框架。我们通过蒸馏和偏好对齐，将一个开源LLM优化为事实摘要器。大量实验表明，EFSum提升了LLM的零样本问答性能，且能够同时保证摘要的有用性和忠实性。
英文摘要：
Recent studies have investigated utilizing Knowledge Graphs (KGs) to enhance Quesetion Answering (QA) performance of Large Language Models (LLMs), yet structured KG verbalization remains challengin. Existing methods, such as triple-form or free-form textual conversion of triple-form facts, encounter several issues. These include reduced evidence density due to duplicated entities or relationships, and reduced evidence clarity due to an inability to emphasize crucial evidence. To address these issues, we propose EFSum, an Evidence-focused Fact Summarization framework for enhanced QA with knowledge-augmented LLMs. We optimize an open-source LLM as a fact summarizer through distillation and preference alignment. Our extensive experiments show that EFSum improves LLM's zero-shot QA performance, and it is possible to ensure both the helpfulness and faithfulness of the summary.
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。
