EUVIMEDEUVIMED entdecken
Crossref

Consensus-Aligned Neuron Efficient Fine-Tuning Large Language Models for Multi-Domain Machine Translation

Shuting Jiang, Ran Song, Yuxin Huang, Yan Xiang, Yantuan Xian, Shengxiang Gao, Zhengtao Yu

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (37) · 31310-31318

DOI: 10.1609/aaai.v40i37.40394 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Shuting Jiang und 6 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multi-domain machine translation (MDMT) aims to build a unified model capable of translating content across diverse domains. Despite the impressive machine translation capabilities demonstrated by large language models (LLMs), domain adaptation still remains a challenge for LLMs. Existing MDMT methods such as in-context learning and parameter-efficient fine-tuning often suffer from domain shift, parameter interference and limited generalization. In this work, we propose a neuron-efficient fine-tuning framework for MDMT that identifies and updates consensus-aligned neurons within LLMs. These neurons are selected by maximizing the mutual information between neuron behavior and domain features, enabling LLMs to capture both generalizable translation patterns and domain-specific nuances. Our method then fine-tunes LLMs guided by these neurons, effectively mitigating parameter interference and domain-specific overfitting. Comprehensive experiments on three LLMs across ten German-English and Chinese-English translation domains evidence that our method consistently outperforms strong PEFT baselines on both seen and unseen domains, achieving state-of-the-art performance.

Zitieren

APA

Jiang, S., Song, R., Huang, Y., Xiang, Y., Xian, Y., Gao, S., & Yu, Z. (2026). Consensus-Aligned Neuron Efficient Fine-Tuning Large Language Models for Multi-Domain Machine Translation. Proceedings of the AAAI Conference on Artificial Intelligence, 40(37), 31310-31318. https://doi.org/10.1609/aaai.v40i37.40394

Vancouver

Jiang S, Song R, Huang Y, Xiang Y, Xian Y, Gao S, et al. Consensus-Aligned Neuron Efficient Fine-Tuning Large Language Models for Multi-Domain Machine Translation. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(37):31310-31318. doi:10.1609/aaai.v40i37.40394

BibTeX
@article{Jiang2026,
  author = {Jiang, Shuting and Song, Ran and Huang, Yuxin and Xiang, Yan and Xian, Yantuan and Gao, Shengxiang and Yu, Zhengtao},
  title = {Consensus-Aligned Neuron Efficient Fine-Tuning Large Language Models for Multi-Domain Machine Translation},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {37},
  pages = {31310--31318},
  doi = {10.1609/aaai.v40i37.40394}
}
Kostenlos starten →