Clickbait Detection via Large Language Models

TL;DR

This paper evaluates the effectiveness of Large Language Models in detecting clickbait headlines in English and Chinese, finding they underperform compared to specialized fine-tuned models.

Contribution

It provides a comprehensive analysis of LLMs' capabilities in clickbait detection, highlighting their limitations in few-shot and zero-shot scenarios.

Findings

LLMs do not outperform state-of-the-art fine-tuned models

LLMs struggle with clickbait detection based solely on headlines

Performance varies across languages and datasets

Abstract

Clickbait, which aims to induce users with some surprising and even thrilling headlines for increasing click-through rates, permeates almost all online content publishers, such as news portals and social media. Recently, Large Language Models (LLMs) have emerged as a powerful instrument and achieved tremendous success in a series of NLP downstream tasks. However, it is not yet known whether LLMs can be served as a high-quality clickbait detection system. In this paper, we analyze the performance of LLMs in the few-shot and zero-shot scenarios on several English and Chinese benchmark datasets. Experimental results show that LLMs cannot achieve the best results compared to the state-of-the-art deep and fine-tuning PLMs methods. Different from human intuition, the experiments demonstrated that LLMs cannot make satisfied clickbait detection just by the headlines.