用多个负例优化大模型，提升历史实体链接准确率。
Beyond Single-Negative Preference: Multi-Negative DPO for LLM-Centric Historical Entity Linking
- 引入多负例直接偏好优化，对比正确实体与所有候选负例
- 在五个语种数据集上超越单负例方法，尤其改善难识别实体
- 适合处理模糊、错字、冷门历史人名的链接任务
大语言模型在历史实体链接任务中展现出潜力，但现有偏好优化通常仅使用每个提及实例中的一个负例，忽略了其余候选实体的信息。本文提出多负例直接偏好优化（MDPO），一种基于参考的成对目标，将正确实体与每个提及关联的所有有效负例进行比较。MDPO保留DPO的Bradley-Terry公式，通过掩码化与长度归一化的序列得分利用完整候选集。在涵盖法语、德语、英语、瑞典语和芬兰语历史报纸文本的hipe-2020和newseye数据集上评估，结果表明MDPO优于监督微调和单负例DPO，尤其在无链接（NIL）提及、语义模糊、OCR噪声及历史难名实体上表现显著提升。进一步分析分离了候选生成与选择错误，揭示候选检索仍是端到端链接的关键瓶颈。结果表明，利用实例内全部负例是一种简单而有效的改进策略。
原文摘要 · Abstract (English)
Large language models (LLMs) have recently shown promise for historical entity linking, but preference optimization for this task is often formulated with only one negative candidate per training instance. This discards information from the remaining candidates retrieved for the same mention. We introduce multi-negative direct preference optimisation (MDPO), a reference-based pairwise objective that compares the correct entity with all valid rejected candidates associated with each mention. MDPO preserves the Bradley-Terry formulation of DPO while exploiting the complete candidate set through masked, length-normalised sequence scores. We evaluate MDPO on hipe-2020 and newseye, covering French, German, English, Swedish, and Finnish historical newspaper text. Experiments show that MDPO improves over supervised fine-tuning and single-negative DPO, with particularly strong gains for NIL mentions, semantic ambiguity, OCR noise, and historically difficult names. Further analyses disentangle candidate-generation and selection errors, showing that candidate retrieval remains a key bottleneck for end-to-end entity linking. These results demonstrate that incorporating all within-instance negative candidates is a simple and effective improvement for LLM-based historical entity linking.
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。