Critic-Driven Decoding for Mitigating Hallucinations in Data-to-text Generation
Identifikátory výsledku
Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3A10475866" target="_blank" >RIV/00216208:11320/23:10475866 - isvavai.cz</a>
Výsledek na webu
<a href="http://dx.doi.org/10.18653/v1/2023.emnlp-main.172" target="_blank" >http://dx.doi.org/10.18653/v1/2023.emnlp-main.172</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.18653/v1/2023.emnlp-main.172" target="_blank" >10.18653/v1/2023.emnlp-main.172</a>
Alternativní jazyky
Jazyk výsledku
angličtina
Název v původním jazyce
Critic-Driven Decoding for Mitigating Hallucinations in Data-to-text Generation
Popis výsledku v původním jazyce
Hallucination of text ungrounded in the input is a well-known problem in neural data-to-text generation. Many methods have been proposed to mitigate it, but they typically require altering model architecture or collecting additional data, and thus cannot be easily applied to an existing model. In this paper, we explore a new way to mitigate hallucinations by combining the probabilistic output of a generator language model (LM) with the output of a special "text critic" classifier, which guides the generation by assessing the match between the input data and the text generated so far. Our method does not need any changes to the underlying LM's architecture or training procedure and can thus be combined with any model and decoding operating on word probabilities. The critic does not need any additional training data, using the base LM's training data and synthetic negative examples. Our experimental results show that our method improves over the baseline on the WebNLG and OpenDialKG benchmarks
Název v anglickém jazyce
Critic-Driven Decoding for Mitigating Hallucinations in Data-to-text Generation
Popis výsledku anglicky
Hallucination of text ungrounded in the input is a well-known problem in neural data-to-text generation. Many methods have been proposed to mitigate it, but they typically require altering model architecture or collecting additional data, and thus cannot be easily applied to an existing model. In this paper, we explore a new way to mitigate hallucinations by combining the probabilistic output of a generator language model (LM) with the output of a special "text critic" classifier, which guides the generation by assessing the match between the input data and the text generated so far. Our method does not need any changes to the underlying LM's architecture or training procedure and can thus be combined with any model and decoding operating on word probabilities. The critic does not need any additional training data, using the base LM's training data and synthetic negative examples. Our experimental results show that our method improves over the baseline on the WebNLG and OpenDialKG benchmarks
Klasifikace
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)
Návaznosti výsledku
Projekt
—
Návaznosti
R - Projekt Ramcoveho programu EK
Ostatní
Rok uplatnění
2023
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Údaje specifické pro druh výsledku
Název statě ve sborníku
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP)
ISBN
979-8-89176-060-8
ISSN
—
e-ISSN
—
Počet stran výsledku
10
Strana od-do
2853-2862
Název nakladatele
Association for Computational Linguistics
Místo vydání
Stroudsburg, PA, USA
Místo konání akce
Singapore
Datum konání akce
6. 12. 2023
Typ akce podle státní příslušnosti
WRD - Celosvětová akce
Kód UT WoS článku
—