10 papers
Efficient Multilingual Reasoning Transfer via Progressive Code-Switching
Zhijun Wang, Junxiao Liu, Hao Zhou +3
Large reasoning models (LRMs) have achieved strong reasoning capabilities in English, yet their performance degrades significantly when required to reason in other languages. A nat…
A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM Integration into Upcycled MoE
Hao Zhou, Tianhao Li, Zhijun Wang +6
Expanding Large Language Models~(LLMs) to new languages is a costly endeavor, demanding extensive Continued Pre-Training~(CPT) and data-intensive alignment. While recent data-free…
Seeing Is No Longer Believing: Frontier Image Generation Models, Synthetic Visual Evidence, and Real-World Risk
Shuai Wu, Xue Li, Yanna Feng +6
Image generation systems can produce plausible photographs, readable documents, and consistent depictions of people and places. When these artifacts are presented as records of rea…
Verbal tics in frontier language models: A critical review of current releases, research evidence, and public discussion
Shuai Wu, Xue Li, Yanna Feng +6
Repeated praise, canned reassurance, familiar contrasts, and conspicuous vocabulary are recurring subjects in discussions of large language models. Their interpretation depends on…
An Inspectable LLM Council for Multi-Model Research Answer Aggregation
Shuai Wu, Xue Li, Yanna Feng +3
Long-form research questions often require answers that combine complementary details, reconcile conflicting estimates, and retain qualifications across several large language mode…
R3S: Refining and Recovering Reinforcement Signals for Multilingual Understanding and Reasoning
Junxiao Liu, Zhijun Wang, Yixiao Li +6
Large reasoning models often default to English reasoning when processing non-English questions, yet their performance drops substantially when reasoning in the question language.…
AdaR: A Framework for Equipping LLMs with Adaptive Reasoning
Zhejian Lai, Xiang Geng, Zhijun Wang +7
Mathematical reasoning is a primary indicator of large language models (LLMs) intelligence. However, existing LLMs exhibit failures in robustness and generalization. This paper att…
Investigating and Scaling up Code-Switching for Multilingual Language Model Pre-Training
Zhijun Wang, Jiahuan Li, Hao Zhou +7
Large language models (LLMs) exhibit remarkable multilingual capabilities despite the extreme language imbalance in the pre-training data. In this paper, we closely examine the rea…
MoE-LPR: Multilingual Extension of Large Language Models through Mixture-of-Experts with Language Priors Routing
Hao Zhou, Zhijun Wang, Shujian Huang +6
Large Language Models (LLMs) are often English-centric due to the disproportionate distribution of languages in their pre-training data. Enhancing non-English language capabilities…
Breaking the Representation Bottleneck of Chinese Characters: Neural Machine Translation with Stroke Sequence Modeling
Zhijun Wang, Xuebo Liu, Min Zhang
Existing research generally treats Chinese character as a minimum unit for representation. However, such Chinese character representation will suffer two bottlenecks: 1) Learning b…