Generating clickbait spoilers with an ensemble of large language models
[ 1 ] Wydział Informatyki i Telekomunikacji, Politechnika Poznańska | [ 2 ] Instytut Informatyki, Wydział Informatyki i Telekomunikacji, Politechnika Poznańska | [ S ] student | [ P ] employee
2023
chapter in monograph / paper
english
EN Clickbait posts are a widespread problem in the webspace. The generation of spoilers, i.e. short texts that neutralize clickbait by providing in- formation that satisfies the curiosity induced by it, is one of the proposed solutions to the problem. Current state-of-the-art methods are based on passage retrieval or question answer- ing approaches and are limited to generating spoilers only in the form of a phrase or a pas- sage. 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 sev- eral non-consecutive parts of text. Experimen- tal evaluation demonstrates that the proposed ensemble model outperforms the baselines in terms of BLEU, METEOR and BERTScore metrics.
431 - 436
CC BY (attribution alone)
publisher's website
final published version
at the time of publication
5
70