Generating clickbait spoilers with an ensemble of large language models

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3A10475934" target="_blank" >RIV/00216208:11320/23:10475934 - isvavai.cz</a>

Výsledek na webu

<a href="https://aclanthology.org/2023.inlg-main.32/" target="_blank" >https://aclanthology.org/2023.inlg-main.32/</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Generating clickbait spoilers with an ensemble of large language models

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

Generating clickbait spoilers with an ensemble of large language models

Popis výsledku anglicky

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.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

R - Projekt Ramcoveho programu EK

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of the 16th International Natural Language Generation Conference

ISBN

979-8-89176-001-1

ISSN

—

e-ISSN

—

Počet stran výsledku

6

Strana od-do

431-436

Název nakladatele

Association for Computational Linguistics

Místo vydání

Stroudsburg, PA, USA

Místo konání akce

Praha, Czechia

Datum konání akce

13. 9. 2023

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—