Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

JointCQ: Improving Factual Hallucination Detection with Joint Claim and Query Generation

Fan Xu, Huixuan Zhang, Zhenliang Zhang, Jiahao Wang, Xiaojun Wan

TL;DR

JointCQ introduces a joint claim–query generator to detect factual hallucinations in open-domain QA. It constructs high-quality training data via criteria-guided filtering and fine-tunes an open-source model to output claims and corresponding retrieval queries in one step. The framework relies on data synthesis from multiple LLMs, retrieval of evidence, and a verifier, achieving state-of-the-art performance on bilingual benchmarks ANAH and HalluQA while maintaining efficiency and accessibility. The work emphasizes transparent verification and low-cost deployment for trustworthy LLM systems.

Abstract

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.

JointCQ: Improving Factual Hallucination Detection with Joint Claim and Query Generation

TL;DR

JointCQ introduces a joint claim–query generator to detect factual hallucinations in open-domain QA. It constructs high-quality training data via criteria-guided filtering and fine-tunes an open-source model to output claims and corresponding retrieval queries in one step. The framework relies on data synthesis from multiple LLMs, retrieval of evidence, and a verifier, achieving state-of-the-art performance on bilingual benchmarks ANAH and HalluQA while maintaining efficiency and accessibility. The work emphasizes transparent verification and low-cost deployment for trustworthy LLM systems.

Abstract

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.
Paper Structure (43 sections, 2 equations, 2 figures, 22 tables)

This paper contains 43 sections, 2 equations, 2 figures, 22 tables.

Table of Contents

  1. Introduction
  2. Hallucination Detection Task
  3. Task Formulation
  4. Pipeline Components
  5. JointCQ Framework
  6. Overview
  7. Data Synthesis
  8. Data Sourcing
  9. Claim Synthesis
  10. Query Synthesis
  11. Criteria-Guided Filtering
  12. Claim Evaluation Criteria
  13. Query Evaluation Criteria
  14. Evaluation Protocol Design
  15. Model Training
  16. ...and 28 more sections

Figures (2)

  • Figure 1: Overview of the JointCQ framework (left) and hallucination detection pipeline (right). The claim-query generator is built with the JointCQ framework and can jointly generate claims and their corresponding queries in a single inference step.
  • Figure 2: An example of the detection process.