把握要点：为零样本关系抽取定制大语言模型
Grasping the Essentials: Tailoring Large Language Models for Zero-Shot Relation Extraction
AI总结：
针对零样本关系抽取缺乏标注且难适应新关系的问题，提出 REPaL，利用 LLM 基于关系定义和未标注语料合成种子，并通过双向 SLM 反馈与多轮迭代提升覆盖、降低偏差。
摘要：
关系抽取（RE）旨在识别文本中实体之间的语义关系。尽管已有相当大的进展，现有模型仍主要需要大量标注训练数据，而收集这些数据成本高昂且耗费人力。此外，这些模型往往难以适应新的或未见过的关系。少样本学习旨在降低标注需求，但通常只能为目标关系提供不完整且有偏的监督，导致性能下降且不稳定。为了在最小化标注需求的同时准确、显式地描述关系语义，我们探索了仅使用定义的零样本关系抽取设置，其中仅使用以自然语言表达的关系定义来训练关系抽取模型。我们提出了 REPaL，包含三个阶段：（1）利用大语言模型（LLM）根据关系定义和未标注语料库生成初始种子实例。（2）使用初始种子微调双向小语言模型（SLM），以学习目标领域的关系。（3）通过整合 SLM 对未标注语料库的预测反馈以及合成历史，扩展模式覆盖并缓解初始种子带来的偏差。为此，我们利用 LLM 的多轮对话能力，在后续对话中结合反馈和合成历史生成新实例。研究表明，面向定义的种子合成能够增强模式覆盖，而不加区分地增加种子数量会导致性能饱和。在两个数据集上的实验表明，REPaL 以显著优势大幅提升了具有成本效益的零样本性能。
英文摘要：
Relation extraction (RE) aims to identify semantic relationships between entities within text. Despite considerable advancements, existing models predominantly require extensive annotated training data, which is both costly and labor-intensive to collect. Moreover, these models often struggle to adapt to new or unseen relations. Few-shot learning, aiming to lessen annotation demands, typically provides incomplete and biased supervision for target relations, leading to degraded and unstable performance. To accurately and explicitly describe relation semantics while minimizing annotation demands, we explore the definition only zero-shot RE setting where only relation definitions expressed in natural language are used to train a RE model. We introduce REPaL, comprising three stages: (1) We leverage large language models (LLMs) to generate initial seed instances from relation definitions and an unlabeled corpus. (2) We fine-tune a bidirectional Small Language Model (SLM) with initial seeds to learn relations for the target domain. (3) We expand pattern coverage and mitigate bias from initial seeds by integrating feedback from the SLM's predictions on the unlabeled corpus and the synthesis history. To accomplish this, we leverage the multi-turn conversation ability of LLMs to generate new instances in follow-up dialogues, informed by both the feedback and synthesis history. Studies reveal that definition-oriented seed synthesis enhances pattern coverage whereas indiscriminately increasing seed quantity leads to performance saturation. Experiments on two datasets show REPaL significantly improved cost-effective zero-shot performance by large margins.
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。
