生成式信息检索中缓解幻觉的遗传方法
Genetic Approach to Mitigate Hallucination in Generative IR
AI总结:
本文提出一种改进的遗传生成方法,通过结合交叉编码器与n-gram重叠度量的平衡适应度函数,在保持高相关性的同时,将有依据答案生成准确率提升四倍,以缓解生成式信息检索中的幻觉问题。
摘要:
生成式语言模型会产生幻觉,即有时会生成事实错误的回复。这些不准确之处尤其隐蔽,因为回复流畅且表达清晰。我们聚焦于有依据答案生成任务(生成式信息检索的一部分),该任务旨在根据搜索引擎检索到的结果直接回答用户问题。我们通过采用一种新的“平衡适应度函数”来改进现有的遗传生成方法,以解决幻觉问题。该函数由一个用于相关性的交叉编码器模型和一个用于促进有依据性的n-gram重叠度量组成。我们的平衡适应度函数方法将有依据答案生成的准确率提高了四倍,同时保持了高相关性。
英文摘要:
Generative language models hallucinate. That is, at times, they generate factually flawed responses. These inaccuracies are particularly insidious because the responses are fluent and well-articulated. We focus on the task of Grounded Answer Generation (part of Generative IR), which aims to produce direct answers to a user's question based on results retrieved from a search engine. We address hallucination by adapting an existing genetic generation approach with a new 'balanced fitness function' consisting of a cross-encoder model for relevance and an n-gram overlap metric to promote grounding. Our balanced fitness function approach quadruples the grounded answer generation accuracy while maintaining high relevance.
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。