Daheim, Nico ; Dziri, Nouha ; Sachan, Mrinmaya ; Gurevych, Iryna ; Ponti, Edoardo (2024)
Elastic Weight Removal for Faithful and Abstractive Dialogue Generation.
2024 Conference of the North American Chapter of the Association for Computational Linguistics. Mexico City, Mexico (17-21.06.2024)
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
Generating factual responses is a crucial requirement for dialogue systems. To promotemore factual responses, a common strategyis to ground their responses in relevant documents that inform response generation. However, common dialogue models still often hallucinate information that was not containedin these documents and is therefore unfaithful. In this work, we propose to alleviate suchhallucinations by ‘subtracting’ the parametersof a model trained to hallucinate from a dialogue response generation model in order to‘negate’ the contribution of such hallucinatedexamples from it. Extensive automatic and human evaluation shows favourable results whencompared to state-of-the-art methods that combine the distributions of multiple models, suchas DExperts (Liu et al., 2021), and others thatchange the training procedure, such as Quark(Lu et al., 2022a). Finally, we show how wecan not only reduce hallucinations but also discourage extractive responses, which are oftena consequence of reducing hallucinations byencouraging copy-pasting of document spans.We publicly release our code for reproducibilityand facilitating further research.
Typ des Eintrags: | Konferenzveröffentlichung |
---|---|
Erschienen: | 2024 |
Autor(en): | Daheim, Nico ; Dziri, Nouha ; Sachan, Mrinmaya ; Gurevych, Iryna ; Ponti, Edoardo |
Art des Eintrags: | Bibliographie |
Titel: | Elastic Weight Removal for Faithful and Abstractive Dialogue Generation |
Sprache: | Englisch |
Publikationsjahr: | Juni 2024 |
Ort: | Mexico City, Mexico |
Verlag: | Association for Computational Linguistics |
Buchtitel: | Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) |
Veranstaltungstitel: | 2024 Conference of the North American Chapter of the Association for Computational Linguistics |
Veranstaltungsort: | Mexico City, Mexico |
Veranstaltungsdatum: | 17-21.06.2024 |
URL / URN: | https://aclanthology.org/2024.naacl-long.393/ |
Kurzbeschreibung (Abstract): | Generating factual responses is a crucial requirement for dialogue systems. To promotemore factual responses, a common strategyis to ground their responses in relevant documents that inform response generation. However, common dialogue models still often hallucinate information that was not containedin these documents and is therefore unfaithful. In this work, we propose to alleviate suchhallucinations by ‘subtracting’ the parametersof a model trained to hallucinate from a dialogue response generation model in order to‘negate’ the contribution of such hallucinatedexamples from it. Extensive automatic and human evaluation shows favourable results whencompared to state-of-the-art methods that combine the distributions of multiple models, suchas DExperts (Liu et al., 2021), and others thatchange the training procedure, such as Quark(Lu et al., 2022a). Finally, we show how wecan not only reduce hallucinations but also discourage extractive responses, which are oftena consequence of reducing hallucinations byencouraging copy-pasting of document spans.We publicly release our code for reproducibilityand facilitating further research. |
Freie Schlagworte: | UKP_p_seditrah_factcheck |
Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Ubiquitäre Wissensverarbeitung |
Hinterlegungsdatum: | 24 Jun 2024 12:36 |
Letzte Änderung: | 05 Aug 2024 09:39 |
PPN: | 52032904X |
Export: | |
Suche nach Titel in: | TUfind oder in Google |
![]() |
Frage zum Eintrag |
Optionen (nur für Redakteure)
![]() |
Redaktionelle Details anzeigen |