用可验证的推理过程提升大模型关系抽取能力
Enhancing Relation Extraction via Supervised Rationale Verification and Feedback
- 设计对比训练的推理监督器，识别并修正错误推理
- 通过反馈修正机制，使模型在关系抽取上显著超越现有方法
- 适合需要高精度关系抽取的场景，如知识图谱构建
尽管现有自动化反馈方法在纠正大语言模型输出方面取得进展，但在关系抽取任务中效果不佳，原因在于其反馈目标和修正方式不适用于该任务。为此，我们提出一种新型自动化反馈框架，引入推理监督器验证推理过程，并提供重新选择的示范作为反馈以修正初始预测。具体地，我们设计因果干预与观测方法，收集有偏与无偏推理用于对比训练推理监督器；随后提出验证-反馈-修正流程，迭代增强模型的关系抽取能力。大量实验表明，该框架显著优于现有方法。
原文摘要 · Abstract (English)
Despite the rapid progress that existing automated feedback methods have made in correcting the output of large language models (LLMs), these methods cannot be well applied to the relation extraction (RE) task due to their designated feedback objectives and correction manner. To address this problem, we propose a novel automated feedback framework for RE, which presents a rationale supervisor to verify the rationale and provides re-selected demonstrations as feedback to correct the initial prediction. Specifically, we first design a causal intervention and observation method to collect biased/unbiased rationales for contrastive training the rationale supervisor. Then, we present a verification-feedback-correction procedure to iteratively enhance LLMs' capability of handling the RE task. Extensive experiments prove that our proposed framework significantly outperforms existing methods.
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。