Hallucination detection is a challenging task for large language models (LLMs), and existing studies heavily rely on powerful closed-source LLMs such as GPT-4. In this paper, we propose an autonomous LLM-based agent framework, called HaluAgent, which enables relatively smaller LLMs (e.g. Baichuan2-Chat 7B) to actively select suitable tools for detecting multiple hallucination types such as text, code, and mathematical expression. In HaluAgent, we integrate the LLM, multi-functional toolbox, and design a fine-grained three-stage detection framework along with memory mechanism. To facilitate the effectiveness of HaluAgent, we leverage existing Chinese and English datasets to synthesize detection trajectories for fine-tuning, which endows HaluAgent with the capability for bilingual hallucination detection. Extensive experiments demonstrate that only using 2K samples for tuning LLMs, HaluAgent can perform hallucination detection on various types of tasks and datasets, achieving performance comparable to or even higher than GPT-4 without tool enhancements on both in-domain and out-of-domain datasets. We release our dataset and code at https://github.com/RUCAIBox/HaluAgent.

通过使用较小型的语言模型以及多功能工具箱，设计了一个细粒度的三阶段检测框架，结合记忆机制，实现了HalullAgent，使其能够主动选择适合的工具来检测多种幻觉类型，包括文本、代码和数学表达式，并利用中英文数据集进行合成检测轨迹以实现双语幻觉检测。大量实验证明，仅使用2K样本进行调优，HaluAgent可以在各种任务和数据集上执行幻觉检测，在领域内和领域外数据集上实现与甚至超过GPT-4的性能而无需工具增强。

小型代理也能出色！强化小型语言模型作为幻觉检测器