用关键要素推理链提升大模型生成带准确数字的新闻标题能力
Teaching Large Language Models Number-Focused Headline Generation With Key Element Rationales
- 通过话题-实体-数值三要素推理链指导模型生成
- 在文本质量和数字准确性上均超越现有方法
- 适合需要精准数字输出的新闻摘要场景
面向需兼具高文本质量与精确数值准确性的数字聚焦型新闻标题生成任务，现有研究或偏重文本质量或仅关注数值推理，难以应对挑战。本文提出一种基于链式思维的框架，利用包含话题（Topic）、实体（Entities）和数值推理（Numerical reasoning）的TEN要素推理作为监督信号，由教师大模型生成，用于指导学生大模型的训练与微调。该方法使学生模型具备自动生成推理链的能力，显著提升数值推理与主题一致性的标题生成性能。实验表明，本方法在文本质量与数值准确性方面均取得更优表现。
原文摘要 · Abstract (English)
Number-focused headline generation is a summarization task requiring both high textual quality and precise numerical accuracy, which poses a unique challenge for Large Language Models (LLMs). Existing studies in the literature focus only on either textual quality or numerical reasoning and thus are inadequate to address this challenge. In this paper, we propose a novel chain-of-thought framework for using rationales comprising key elements of the Topic, Entities, and Numerical reasoning (TEN) in news articles to enhance the capability for LLMs to generate topic-aligned high-quality texts with precise numerical accuracy. Specifically, a teacher LLM is employed to generate TEN rationales as supervision data, which are then used to teach and fine-tune a student LLM. Our approach teaches the student LLM automatic generation of rationales with enhanced capability for numerical reasoning and topic-aligned numerical headline generation. Experiments show that our approach achieves superior performance in both textual quality and numerical accuracy.
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。