Clickbait posts are a widespread problem in the webspace. The generation of spoilers, i.e. short texts that neutralize clickbait by providing information that makes it uninteresting, is one of the proposed solutions to the problem. Current state-of-the-art methods are based on passage retrieval or question answering approaches and are limited to generating spoilers only in the form of a phrase or a passage. In this work, we propose an ensemble of fine-tuned large language models for clickbait spoiler generation. Our approach is not limited to phrase or passage spoilers, but is also able to generate multipart spoilers that refer to several non-consecutive parts of text. Experimental evaluation demonstrates that the proposed ensemble model outperforms the baselines in terms of BLEU, METEOR and BERTScore metrics.

Clickbait posts are a common problem on social media platforms, as they often deceive users by providing misleading or sensational headlines that do not match the content of the linked web page. The aim of this study is to create a technique for identifying the specific type of suitable spoiler - be it a phrase, a passage, or a multipart spoiler - needed to neutralize clickbait posts. This is achieved by developing a machine learning classifier analyzing both the clickbait post and the linked web page. Modern approaches for constructing a text classifier usually rely on fine-tuning a transformer-based model pre-trained on large unsupervised corpora. However, recent advances in the development of large-scale language models have led to the emergence of a new transfer learning paradigm based on prompt engineering. In this work, we study these two transfer learning techniques and compare their effectiveness for clickbait spoiler-type detection task. Our experimental results show that for this task, using the standard fine-tuning method gives better results than using prompting. The best model can achieve a similar performance to that presented by Hagen et al. (2022).