Teaching Large Language Models Number-Focused Headline Generation With Key Element Rationales

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Qian, Zhen, Zhang, Xiuzhen, Xu, Xiaofei, Xia, Feng
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909478311428096
author Qian, Zhen
Zhang, Xiuzhen
Xu, Xiaofei
Xia, Feng
author_facet Qian, Zhen
Zhang, Xiuzhen
Xu, Xiaofei
Xia, Feng
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2502_03129
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Teaching Large Language Models Number-Focused Headline Generation With Key Element Rationales
Qian, Zhen
Zhang, Xiuzhen
Xu, Xiaofei
Xia, Feng
Computation and Language
Machine Learning
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.
title Teaching Large Language Models Number-Focused Headline Generation With Key Element Rationales
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2502.03129