Unraveling the Capabilities of Language Models in News Summarization

TL;DR

This paper benchmarks 20 recent language models for news summarization, revealing that larger models like GPT-3.5-Turbo and GPT-4 excel, while some smaller models also show promising results, with demonstration examples not always improving performance.

Contribution

It provides a comprehensive evaluation of various language models in zero-shot and few-shot settings for news summarization, highlighting the impact of reference quality and model capabilities.

Findings

GPT-3.5-Turbo and GPT-4 outperform others in summarization quality.

Few-shot demonstrations sometimes worsen results due to poor reference summaries.

Certain smaller models like Qwen1.5-7B show competitive performance.

Abstract

Given the recent introduction of multiple language models and the ongoing demand for improved Natural Language Processing tasks, particularly summarization, this work provides a comprehensive benchmarking of 20 recent language models, focusing on smaller ones for the news summarization task. In this work, we systematically test the capabilities and effectiveness of these models in summarizing news article texts which are written in different styles and presented in three distinct datasets. Specifically, we focus in this study on zero-shot and few-shot learning settings and we apply a robust evaluation methodology that combines different evaluation concepts including automatic metrics, human evaluation, and LLM-as-a-judge. Interestingly, including demonstration examples in the few-shot learning setting did not enhance models' performance and, in some cases, even led to worse quality of the generated summaries. This issue arises mainly due to the poor quality of the gold summaries that have been used as reference summaries, which negatively impacts the models' performance. Furthermore, our study's results highlight the exceptional performance of GPT-3.5-Turbo and GPT-4, which generally dominate due to their advanced capabilities. However, among the public models evaluated, certain models such as Qwen1.5-7B, SOLAR-10.7B-Instruct-v1.0, Meta-Llama-3-8B and Zephyr-7B-Beta demonstrated promising results. These models showed significant potential, positioning them as competitive alternatives to large models for the task of news summarization.