Mitigating Hallucinations and Off-target Machine Translation with Source-Contrastive and Language-Contrastive Decoding

Rico Sennrich, Jannis Vamvas, Alireza Mohammadshahi


Abstract
Hallucinations and off-target translation remain unsolved problems in MT, especially for low-resource languages and massively multilingual models. In this paper, we introduce two related methods to mitigate these failure cases with a modified decoding objective, without either requiring retraining or external models. In source-contrastive decoding, we search for a translation that is probable given the correct input, but improbable given a random input segment. In language-contrastive decoding, we search for a translation that is probable, but improbable given the wrong language indicator token. Experiments on the massively multilingual models M2M-100 (418M) and SMaLL-100 show that these methods suppress hallucinations and off-target translations, reducing the number of translations with segment-level chrF2 below 10 by 67-83% on average across 57 tested translation directions. In a proof of concept on out-of-English translation, we also show that we can suppress off-target translations with large language models. We release code upon acceptance.
Anthology ID:
2024.eacl-short.4
Volume:
Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:
March
Year:
2024
Address:
St. Julian’s, Malta
Editors:
Yvette Graham, Matthew Purver
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
21–33
Language:
URL:
https://preview.aclanthology.org/build-pipeline-with-new-library/2024.eacl-short.4/
DOI:
Bibkey:
Cite (ACL):
Rico Sennrich, Jannis Vamvas, and Alireza Mohammadshahi. 2024. Mitigating Hallucinations and Off-target Machine Translation with Source-Contrastive and Language-Contrastive Decoding. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers), pages 21–33, St. Julian’s, Malta. Association for Computational Linguistics.
Cite (Informal):
Mitigating Hallucinations and Off-target Machine Translation with Source-Contrastive and Language-Contrastive Decoding (Sennrich et al., EACL 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/build-pipeline-with-new-library/2024.eacl-short.4.pdf
Software:
 2024.eacl-short.4.software.zip
Video:
 https://preview.aclanthology.org/build-pipeline-with-new-library/2024.eacl-short.4.mp4