用遗传算法优化生成答案，让大模型少说假话。
Genetic Approach to Mitigate Hallucination in Generative IR
- 引入平衡适应度函数，结合相关性与词元重叠度
- 答案准确率提升至四倍，同时保持高相关性
- 适合需要可靠回答的问答系统开发者
生成式语言模型会产生幻觉，即生成看似合理但事实错误的回答。本文聚焦于基于检索结果的有根据答案生成任务（生成式信息检索的一部分），通过改进现有遗传生成方法，提出一种新的‘平衡适应度函数’，包含交叉编码器用于判断相关性，以及n-gram重叠度指标以增强答案的可依据性。该方法使有根据的答案生成准确率提升四倍，同时维持高相关性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。