Clickbait Detection via Large Language Models
This work addresses the problem of clickbait detection for online content platforms, but it is incremental as it primarily evaluates existing LLMs without introducing new methods.
The paper investigated whether large language models (LLMs) can effectively detect clickbait from headlines in few-shot and zero-shot scenarios, finding that they underperform compared to state-of-the-art fine-tuned methods and fail to meet expectations based on human intuition.
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.