Imitating Human Reasoning to Extract 5W1H in News

Simple item page
dc.catalogadorvdr
dc.contributor.authorMuñoz Castro, Carlos José
dc.contributor.authorMendoza Rocha, Marcelo
dc.contributor.authorLöbel Díaz, Hans-Albert
dc.contributor.authorKeith, Brian
dc.date.accessioned2025-05-27T15:23:34Z
dc.date.available2025-05-27T15:23:34Z
dc.date.issued2025
dc.description.abstractExtracting key information from news articles is crucial for advancing search systems. Historically, the 5W1H framework, which organises information based on ’Who’, ’What’, ’When’, ’Where’, ’Why’, and ’How’, has been a predominant method in digital journalism empowering search tools. The rise of Large Language Models (LLMs) has sparked new research into their potential for performing such information extraction tasks effectively. Our study examines a novel approach to employing LLMs in the 5W1H extraction process, particularly focusing on their capacity to mimic human reasoning. We introduce two innovative Chain-of-Thought (COT) prompting techniques to extract 5W1H in news: extractive reasoning and question-level reasoning. The former directs the LLM to pinpoint and highlight essential details from texts, while the latter encourages the model to emulate human-like reasoning at the question-response level. Our research methodology includes experiments with leading LLMs using prompting strategies to ascertain the most effective approach. The results indicate that COT prompting significantly outperforms other methods. In addition, we show that the effectiveness of LLMs in such tasks depends greatly on the nature of the questions posed.
dc.fechaingreso.objetodigitalNo aplica
dc.format.extent5 páginas
dc.fuente.origenORCID
dc.identifier.doi10.1145/3701716.3715532
dc.identifier.urihttps://doi.org/10.1145/3701716.3715532
dc.identifier.urihttps://repositorio.uc.cl/handle/11534/104487
dc.information.autorucEscuela de Ingeniería; Mendoza Rocha, Marcelo; S/I; 1237020
dc.information.autorucEscuela de Ingeniería; Löbel Díaz, Hans-Albert; 0000-0003-3514-9414; 131278
dc.language.isoen
dc.nota.accesoSin adjunto
dc.pagina.final1203
dc.pagina.inicio1999
dc.publisherACM Digital Library
dc.relation.isformatofWWW '25: Companion Proceedings of the ACM on Web Conference 2025 (2025, Nueva York, Estados Unidos)
dc.rightsacceso restringido
dc.subject5W1H
dc.subjectLLM
dc.subjectImitative reasoning
dc.subjectNews
dc.subject.ddc620
dc.subject.deweyIngenieríaes_ES
dc.subject.ods09 Industry, innovation and infrastructure
dc.subject.odspa09 Industria, innovación e infraestructura
dc.titleImitating Human Reasoning to Extract 5W1H in News
dc.typecomunicación de congreso
sipa.codpersvinculados1237020
sipa.codpersvinculados131278
sipa.trazabilidadORCID;2025-05-26
Files
Collections
Artículos de conferencia