解决扩散语言模型的单向偏见问题，提升双向关系理解能力
DiffER: Diffusion Entity-Relation Modeling for Reversal Curse in Diffusion Large Language Models
- 通过全实体掩码实现整体实体预测，缓解实体碎片化
- 构建对称数据分布并增强关系信息，减少数据偏差
- 适用于需精准理解实体关系的任务，如知识推理
反转诅咒指大型语言模型在处理逻辑双向关系时表现出明显的单向行为。尽管扩散语言模型（DLLMs）采用双向训练，仍存在此问题。我们系统实验发现其根源在于：1）训练中实体碎片化；2）数据不对称；3）缺失实体关系。为此提出DiffER方法，通过全实体掩码避免实体被拆分，结合分布对称与关系增强的数据构建策略，缓解数据偏差与关系缺失。大量实验表明，DiffER能有效缓解扩散语言模型中的反转诅咒，为未来研究提供新视角。
原文摘要 · Abstract (English)
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.
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。