联合生成事实声明与查询，减少大模型幻觉检测中的信息丢失。
JointCQ: Improving Factual Hallucination Detection with Joint Claim and Query Generation
- 联合建模声明提取与查询生成，避免上下文丢失。
- 在多个开放域问答数据集上超越现有方法，提升检测准确率。
- 适合需要高可信度生成内容的AI系统开发者使用。
当前大语言模型常出现幻觉问题，即生成看似真实但实际不可靠的内容。典型的幻觉检测流程包括响应分解（如声明提取）、查询生成、证据收集（搜索或检索）和声明验证。然而，现有方法在前两个阶段存在局限，如声明提取时的信息丢失、查询生成缺乏特异性，导致整体检测性能下降。本文提出JointCQ（https://github.com/pku0xff/JointCQ），一种联合声明与查询生成框架，通过精心设计的评估标准筛选训练数据，并微调语言模型以实现声明提取与查询生成的联合优化，为下游搜索与验证提供可靠且信息丰富的输入。实验结果表明，该方法在多个开放域问答幻觉检测基准上优于先前方法，推动更可信、透明的语言模型系统发展。
原文摘要 · Abstract (English)
Current large language models (LLMs) often suffer from hallucination issues, i,e, generating content that appears factual but is actually unreliable. A typical hallucination detection pipeline involves response decomposition (i.e., claim extraction), query generation, evidence collection (i.e., search or retrieval), and claim verification. However, existing methods exhibit limitations in the first two stages, such as context loss during claim extraction and low specificity in query generation, resulting in degraded performance across the hallucination detection pipeline. In this work, we introduce JointCQ https://github.com/pku0xff/JointCQ, a joint claim-and-query generation framework designed to construct an effective and efficient claim-query generator. Our framework leverages elaborately designed evaluation criteria to filter synthesized training data, and finetunes a language model for joint claim extraction and query generation, providing reliable and informative inputs for downstream search and verification. Experimental results demonstrate that our method outperforms previous methods on multiple open-domain QA hallucination detection benchmarks, advancing the goal of more trustworthy and transparent language model systems.
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。