Thinker-DDM: Modeling Deliberation for Machine Translation with a Drift-Diffusion Process

Hongbin Na, Zimu Wang, Mieradilijiang Maimaiti, Tong Chen, Wei Wang, Tao Shen, Ling Chen


Abstract
Large language models (LLMs) have demonstrated promising potential in various downstream tasks, including machine translation. However, prior work on LLM-based machine translation has mainly focused on better utilizing training data, demonstrations, or pre-defined and universal knowledge to improve performance, with a lack of consideration of decision-making like human translators. In this paper, we incorporate Thinker with the Drift-Diffusion Model (Thinker-DDM) to address this issue. We then redefine the Drift-Diffusion process to emulate human translators’ dynamic decision-making under constrained resources. We conduct extensive experiments under the high-resource, low-resource, and commonsense translation settings using the WMT22 and CommonMT datasets, in which Thinker-DDM outperforms baselines in the first two scenarios. We also perform additional analysis and evaluation on commonsense translation to illustrate the high effectiveness and efficacy of the proposed method.
Anthology ID:
2025.alta-main.4
Volume:
Proceedings of the 23rd Annual Workshop of the Australasian Language Technology Association
Month:
November
Year:
2025
Address:
Sydney, Australia
Editors:
Jonathan K. Kummerfeld, Aditya Joshi, Mark Dras
Venues:
ALTA | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
45–63
Language:
URL:
https://aclanthology.org/2025.alta-main.4/
DOI:
Bibkey:
Cite (ACL):
Hongbin Na, Zimu Wang, Mieradilijiang Maimaiti, Tong Chen, Wei Wang, Tao Shen, and Ling Chen. 2025. Thinker-DDM: Modeling Deliberation for Machine Translation with a Drift-Diffusion Process. In Proceedings of the 23rd Annual Workshop of the Australasian Language Technology Association, pages 45–63, Sydney, Australia. Association for Computational Linguistics.
Cite (Informal):
Thinker-DDM: Modeling Deliberation for Machine Translation with a Drift-Diffusion Process (Na et al., ALTA 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.alta-main.4.pdf