5 papers
LANG: Reinforcement Learning for Multilingual Reasoning with Language-Adaptive Hint Guidance
Yuchun Fan, Bei Li, Peiguang Li +9
Reinforcement learning has proven effective for enhancing multi-step reasoning in large language models (LLMs), yet its benefits have not fully translated to multilingual contexts.…
Preferences Order, Ratings Anchor: From Fused Expert Aesthetic Ground Truth to Self-Distillation
Yuanpei Zhao, Jie Lin, Chao Zhang +5
Pairwise preferences and pointwise ratings are the two dominant annotation protocols in image aesthetic assessment (IAA), yet existing benchmarks adopt only one, leaving their comp…
DaPT: A Dual-Path Framework for Multilingual Multi-hop Question Answering
Yilin Wang, Yuchun Fan, Jiaoyang Li +5
Retrieval-augmented generation (RAG) systems have made significant progress in solving complex multi-hop question answering (QA) tasks in the English scenario. However, RAG systems…
Language-Specific Layer Matters: Efficient Multilingual Enhancement for Large Vision-Language Models
Yuchun Fan, Yilin Wang, Yongyu Mu +5
Large vision-language models (LVLMs) have demonstrated exceptional capabilities in understanding visual information with human languages but also exhibit an imbalance in multilingu…
SLAM: Towards Efficient Multilingual Reasoning via Selective Language Alignment
Yuchun Fan, Yongyu Mu, Yilin Wang +7
Despite the significant improvements achieved by large language models (LLMs) in English reasoning tasks, these models continue to struggle with multilingual reasoning. Recent stud…