每一步都重要：将解码轨迹解码为dLLMs的作者指纹
Every Step Counts: Decoding Trajectories as Authorship Fingerprints of dLLMs
AI总结：
本文提出有向解码图和高斯轨迹归因方法，利用离散扩散大语言模型的解码轨迹结构信息进行模型归因，有效区分不同模型及其检查点。
摘要：
离散扩散大语言模型（dLLMs）近期已成为非自回归语言建模的一种有竞争力的范式。其独特的解码机制能够实现更快的推理速度，并在代码生成和数学任务中展现出强劲性能。在本工作中，我们表明dLLMs的解码机制不仅增强了模型的实用性，还可作为模型归因的强大工具。该问题的一个关键挑战在于归因场景的多样性，包括区分不同模型以及区分同一模型的不同检查点或备份。为确保广泛适用性，我们确定了两个基本问题：从解码轨迹中提取什么信息，以及如何有效利用这些信息。我们首先观察到，直接依赖每步的模型置信度会导致性能不佳。这主要归因于dLLMs的双向解码特性：每个新解码的token会影响其他已解码token的置信度，使得模型置信度高度冗余，并掩盖了关于解码顺序或依赖关系的结构信号。为克服此问题，我们提出了一种新颖的信息提取方案，称为有向解码图（DDM），该方案捕获解码步骤之间的结构关系，并更好地揭示模型特定行为。此外，为在归因过程中充分利用提取的结构信息，我们提出了高斯轨迹归因（GTA）方法，即为每个目标模型在每个解码位置拟合一个逐单元的高斯分布，并将轨迹的似然定义为归因分数：如果一条轨迹在特定模型的分布下表现出更高的对数似然，则该轨迹更可能由该模型生成。在不同设置下的大量实验验证了我们方法的有效性。
英文摘要：
Discrete Diffusion Large Language Models (dLLMs) have recently emerged as a competitive paradigm for non-autoregressive language modeling. Their distinctive decoding mechanism enables faster inference speed and strong performance in code generation and mathematical tasks. In this work, we show that the decoding mechanism of dLLMs not only enhances model utility but also can be used as a powerful tool for model attribution. A key challenge in this problem lies in the diversity of attribution scenarios, including distinguishing between different models as well as between different checkpoints or backups of the same model. To ensure broad applicability, we identify two fundamental problems: what information to extract from the decoding trajectory, and how to utilize it effectively. We first observe that relying directly on per-step model confidence yields poor performance. This is mainly due to the bidirectional decoding nature of dLLMs: each newly decoded token influences the confidence of other decoded tokens, making model confidence highly redundant and washing out structural signal regarding decoding order or dependencies. To overcome this, we propose a novel information extraction scheme called the Directed Decoding Map (DDM), which captures structural relationships between decoding steps and better reveals model-specific behaviors. Furthermore, to make full use of the extracted structural information during attribution, we propose Gaussian-Trajectory Attribution (GTA), where we fit a cell-wise Gaussian distribution at each decoding position for each target model, and define the likelihood of a trajectory as the attribution score: if a trajectory exhibits higher log-likelihood under the distribution of a specific model, it is more likely to have been generated by that model. Extensive experiments under different settings validate the utility of our methods.
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。
