DiffER: 用于扩散大语言模型中反转诅咒的扩散实体-关系建模
DiffER: Diffusion Entity-Relation Modeling for Reversal Curse in Diffusion Large Language Models
AI总结：
DiffER通过实体感知训练和平衡数据构建，解决扩散大语言模型中的反转诅咒问题。
摘要：
'反转诅咒'指的是大型语言模型（LLMs）在处理逻辑双向关系时表现出主要单向行为的现象。先前的研究将此归因于自回归训练——预测下一个标记本质上倾向于信息流从左到右，而不是真正的双向知识关联。然而，我们发现扩散语言模型（DLLMs），尽管是双向训练的，也受到反转诅咒的影响。为了调查根本原因，我们在DLLMs上进行了系统实验，并识别出三个关键原因：1）训练中的实体碎片化，2）数据不对称，3）缺失的实体关系。受这些原因分析的启发，我们提出了扩散实体-关系建模（DiffER），通过实体感知训练和平衡数据构建来解决反转诅咒。具体而言，DiffER引入了整体实体遮蔽，通过单步预测完整实体来缓解实体碎片化。DiffER进一步采用分布对称和关系增强的数据构建策略来缓解数据不对称和缺失关系。广泛实验表明，DiffER有效缓解了扩散语言模型中的反转诅咒，为未来研究提供了新的视角。
英文摘要：
The "reversal curse" refers to the phenomenon where large language models (LLMs) exhibit predominantly unidirectional behavior when processing logically bidirectional relationships. Prior work attributed this to autoregressive training -- predicting the next token inherently favors left-to-right information flow over genuine bidirectional knowledge associations. However, we observe that Diffusion LLMs (DLLMs), despite being trained bidirectionally, also suffer from the reversal curse. To investigate the root causes, we conduct systematic experiments on DLLMs and identify three key reasons: 1) entity fragmentation during training, 2) data asymmetry, and 3) missing entity relations. Motivated by the analysis of these reasons, we propose Diffusion Entity-Relation Modeling (DiffER), which addresses the reversal curse through entity-aware training and balanced data construction. Specifically, DiffER introduces whole-entity masking, which mitigates entity fragmentation by predicting complete entities in a single step. DiffER further employs distribution-symmetric and relation-enhanced data construction strategies to alleviate data asymmetry and missing relations. Extensive experiments demonstrate that DiffER effectively alleviates the reversal curse in Diffusion LLMs, offering new perspectives for future research.
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。
