Financial News Summarization: Can extractive methods still offer a true alternative to LLMs?

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Reche, Nicolas, Linhares-Pontes, Elvys, Torres-Moreno, Juan-Manuel
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918239821365248
author Reche, Nicolas
Linhares-Pontes, Elvys
Torres-Moreno, Juan-Manuel
author_facet Reche, Nicolas
Linhares-Pontes, Elvys
Torres-Moreno, Juan-Manuel
contents Financial markets change rapidly due to news, economic shifts, and geopolitical events. Quick reactions are vital for investors to avoid losses or capture short-term gains. As a result, concise financial news summaries are critical for decision-making. With over 50,000 financial articles published daily, automation in summarization is necessary. This study evaluates a range of summarization methods, from simple extractive techniques to advanced large language models (LLMs), using the FinLLMs Challenge dataset. LLMs generated more coherent and informative summaries, but they are resource-intensive and prone to hallucinations, which can introduce significant errors into financial summaries. In contrast, extractive methods perform well on short, well-structured texts and offer a more efficient alternative for this type of article. The best ROUGE results come from fine-tuned LLM model like FT-Mistral-7B, although our data corpus has limited reliability, which calls for cautious interpretation.
format Preprint
id arxiv_https___arxiv_org_abs_2512_08764
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Financial News Summarization: Can extractive methods still offer a true alternative to LLMs?
Reche, Nicolas
Linhares-Pontes, Elvys
Torres-Moreno, Juan-Manuel
Computational Engineering, Finance, and Science
Financial markets change rapidly due to news, economic shifts, and geopolitical events. Quick reactions are vital for investors to avoid losses or capture short-term gains. As a result, concise financial news summaries are critical for decision-making. With over 50,000 financial articles published daily, automation in summarization is necessary. This study evaluates a range of summarization methods, from simple extractive techniques to advanced large language models (LLMs), using the FinLLMs Challenge dataset. LLMs generated more coherent and informative summaries, but they are resource-intensive and prone to hallucinations, which can introduce significant errors into financial summaries. In contrast, extractive methods perform well on short, well-structured texts and offer a more efficient alternative for this type of article. The best ROUGE results come from fine-tuned LLM model like FT-Mistral-7B, although our data corpus has limited reliability, which calls for cautious interpretation.
title Financial News Summarization: Can extractive methods still offer a true alternative to LLMs?
topic Computational Engineering, Finance, and Science
url https://arxiv.org/abs/2512.08764