6 papers · 1 filter
Why Not Transform Chat Large Language Models to Non-English?
Xiang Geng, Ming Zhu, Jiahuan Li +14
The scarcity of non-English data limits the development of non-English large language models (LLMs). Transforming English-centric LLMs to non-English has been identified as an effe…
SDGO: Self-Discrimination-Guided Optimization for Consistent Safety in Large Language Models
Peng Ding, Wen Sun, Dailin Li +4
Large Language Models (LLMs) excel at various natural language processing tasks but remain vulnerable to jailbreaking attacks that induce harmful content generation. In this paper,…
Trans-Zero: Self-Play Incentivizes Large Language Models for Multilingual Translation Without Parallel Data
Wei Zou, Sen Yang, Yu Bao +3
The rise of Large Language Models (LLMs) has reshaped machine translation (MT), but multilingual MT still relies heavily on parallel data for supervised fine-tuning (SFT), facing c…
Extend Adversarial Policy Against Neural Machine Translation via Unknown Token
Wei Zou, Shujian Huang, Jiajun Chen
Generating adversarial examples contributes to mainstream neural machine translation~(NMT) robustness. However, popular adversarial policies are apt for fixed tokenization, hinderi…
Improved Paraphrase Generation via Controllable Latent Diffusion
Wei Zou, Ziyuan Zhuang, Xiang Geng +3
Paraphrase generation strives to generate high-quality and diverse expressions of a given text, a domain where diffusion models excel. Though SOTA diffusion generation reconciles g…
MAPO: Advancing Multilingual Reasoning through Multilingual Alignment-as-Preference Optimization
Shuaijie She, Wei Zou, Shujian Huang +4
Though reasoning abilities are considered language-agnostic, existing LLMs exhibit inconsistent reasoning abilities across different languages, e.g., reasoning in the dominant lang…