EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Hallucinations in Large Multilingual Translation Models

Nuno M. Guerreiro, Duarte M. Alves, Jonas Waldendorf, Barry Haddow, Alexandra Birch, Pierre Colombo, André F. T. Martins

Transactions of the Association for Computational Linguistics · 14.12.2023 · 11 · 1500-1517

DOI: 10.1162/tacl_a_00615 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Transactions of the Association for Computational Linguistics, online erschienen am 14.12.2023. Verfasst von Nuno M. Guerreiro und 6 weiteren Autor:innen. Die Arbeit wurde bisher 112-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Hallucinated translations can severely undermine and raise safety issues when machine translation systems are deployed in the wild. Previous research on the topic focused on small bilingual models trained on high-resource languages, leaving a gap in our understanding of hallucinations in multilingual models across diverse translation scenarios. In this work, we fill this gap by conducting a comprehensive analysis—over 100 language pairs across various resource levels and going beyond English-centric directions—on both the M2M neural machine translation (NMT) models and GPT large language models (LLMs). Among several insights, we highlight that models struggle with hallucinations primarily in low-resource directions and when translating out of English, where, critically, they may reveal toxic patterns that can be traced back to the training data. We also find that LLMs produce qualitatively different hallucinations to those of NMT models. Finally, we show that hallucinations are hard to reverse by merely scaling models trained with the same data. However, employing more diverse models, trained on different data or with different procedures, as fallback systems can improve translation quality and virtually eliminate certain pathologies.

Zitieren

APA

Guerreiro, N. M., Alves, D. M., Waldendorf, J., Haddow, B., Birch, A., Colombo, P., & Martins, A. F. T. (2023). Hallucinations in Large Multilingual Translation Models. Transactions of the Association for Computational Linguistics, 11, 1500-1517. https://doi.org/10.1162/tacl_a_00615

Vancouver

Guerreiro NM, Alves DM, Waldendorf J, Haddow B, Birch A, Colombo P, et al. Hallucinations in Large Multilingual Translation Models. Transactions of the Association for Computational Linguistics. 2023;11:1500-1517. doi:10.1162/tacl_a_00615

BibTeX
@article{Guerreiro2023,
  author = {Guerreiro, Nuno M. and Alves, Duarte M. and Waldendorf, Jonas and Haddow, Barry and Birch, Alexandra and Colombo, Pierre and Martins, André F. T.},
  title = {Hallucinations in Large Multilingual Translation Models},
  journal = {Transactions of the Association for Computational Linguistics},
  year = {2023},
  volume = {11},
  pages = {1500--1517},
  doi = {10.1162/tacl_a_00615}
}
Kostenlos starten →