arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2510.01274cs.CLcs.LG
收藏

TraceDet:从扩散大语言模型的解码轨迹中检测幻觉

TraceDet: Hallucination Detection from the Decoding Trace of Diffusion Large Language Models

Department of Engineering Science, University of Oxford, UK(牛津大学工程科学系);Hasso Plattner Institute, University of Potsdam(波茨坦大学哈索普兰特纳研究所);Carnegie Mellon University(卡内基梅隆大学);Mohamed bin Zayed University of Artificial Intelligence(姆罕默德·本·拉希德智能大学)

Shenxu Chang, Junchi Yu, Weixing Wang, Yongqiang Chen, Jialin Yu, Philip Torr, Jindong Gu

AI总结:

针对现有AR-LLM幻觉检测方法不适用于D-LLM的问题,提出TraceDet框架,利用D-LLM多步去噪的中间轨迹信号检测幻觉,在多个开源D-LLM上AUROC较基线平均提升15.2%。

摘要:

扩散大语言模型(D-LLM)近期已成为自回归大语言模型(AR-LLM)的一类有前景的替代方案。然而,D-LLM中的幻觉问题仍未得到充分研究,限制了其在实际应用中的可靠性。现有幻觉检测方法是为AR-LLM设计的,依赖单步生成的信号,因此不适用于幻觉信号往往贯穿多步去噪过程的D-LLM。为填补这一空白,我们提出了TraceDet,这是一种新颖的框架,明确利用D-LLM的中间去噪步骤进行幻觉检测。TraceDet将去噪过程建模为动作轨迹,每个动作被定义为模型基于先前中间输出对净化后响应的预测。通过识别对幻觉响应信息量最大的子轨迹,TraceDet利用D-LLM多步去噪过程中的关键幻觉信号进行幻觉检测。在多种开源D-LLM上开展的大量实验表明,TraceDet持续提升了幻觉检测效果,与基线方法相比,AUROC平均提升了15.2%。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑