Kun Gai, Junyi Li, Ji-Rong Wen, Wayne Zhao, Di Zhang, Hongzhi Zhang, Fuzheng Zhang, Xiaoxue Cheng
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.
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 1 (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 indomain and out-of-domain datasets. We release our dataset and code at https://github.com/ RUCAIBox/HaluAgent.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2406.11277")
get_code_for_paper("2406.11277")
have("2406.11277")
Connect an agent — have() is free.