@inproceedings{cheng-etal-2024-small,
    title = "Small Agent Can Also Rock! Empowering Small Language Models as Hallucination Detector",
    author = "Cheng, Xiaoxue  and
      Li, Junyi  and
      Zhao, Xin  and
      Zhang, Hongzhi  and
      Zhang, Fuzheng  and
      Zhang, Di  and
      Gai, Kun  and
      Wen, Ji-Rong",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.emnlp-main.809/",
    doi = "10.18653/v1/2024.emnlp-main.809",
    pages = "14600--14615",
    abstract = "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."
}