通过分析扩散模型的去噪过程，精准识别幻觉内容。
TraceDet: Hallucination Detection from the Decoding Trace of Diffusion Large Language Models
- 利用多步去噪过程中的中间输出构建动作轨迹
- 在多个开源扩散模型上实现平均15.2%的检测性能提升
- 适合关注扩散语言模型可靠性与安全性的研究者
扩散型大语言模型（D-LLMs）作为自回归模型（AR-LLMs）的潜在替代方案备受关注，但其幻觉问题尚未得到充分研究，限制了实际应用中的可靠性。现有检测方法针对AR-LLMs设计，依赖单步生成信号，难以捕捉D-LLMs中贯穿多步去噪过程的幻觉线索。为此，我们提出TraceDet框架，将去噪过程建模为动作轨迹，每个动作定义为基于前序中间输出对纯净响应的预测。通过识别对幻觉响应最具信息量的子轨迹，TraceDet有效利用多步去噪过程中的关键幻觉信号。在多个开源D-LLMs上的大量实验表明，TraceDet显著提升幻觉检测能力，平均AUROC提升15.2%。
原文摘要 · Abstract (English)
Diffusion large language models (D-LLMs) have recently emerged as a promising alternative to auto-regressive LLMs (AR-LLMs). However, the hallucination problem in D-LLMs remains underexplored, limiting their reliability in real-world applications. Existing hallucination detection methods are designed for AR-LLMs and rely on signals from single-step generation, making them ill-suited for D-LLMs where hallucination signals often emerge throughout the multi-step denoising process. To bridge this gap, we propose TraceDet, a novel framework that explicitly leverages the intermediate denoising steps of D-LLMs for hallucination detection. TraceDet models the denoising process as an action trace, with each action defined as the model's prediction over the cleaned response, conditioned on the previous intermediate output. By identifying the sub-trace that is maximally informative to the hallucinated responses, TraceDet leverages the key hallucination signals in the multi-step denoising process of D-LLMs for hallucination detection. Extensive experiments on various open source D-LLMs demonstrate that TraceDet consistently improves hallucination detection, achieving an average gain in AUROC of 15.2% compared to baselines.
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。