Generating clickbait spoilers with an ensemble of large language models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Woźny, Mateusz, Lango, Mateusz
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911887447293952
author Woźny, Mateusz
Lango, Mateusz
author_facet Woźny, Mateusz
Lango, Mateusz
contents Clickbait posts are a widespread problem in the webspace. The generation of spoilers, i.e. short texts that neutralize clickbait by providing information 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 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.
format Preprint
id arxiv_https___arxiv_org_abs_2405_16284
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Generating clickbait spoilers with an ensemble of large language models
Woźny, Mateusz
Lango, Mateusz
Computation and Language
Information Retrieval
Clickbait posts are a widespread problem in the webspace. The generation of spoilers, i.e. short texts that neutralize clickbait by providing information 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 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.
title Generating clickbait spoilers with an ensemble of large language models
topic Computation and Language
Information Retrieval
url https://arxiv.org/abs/2405.16284