5 papers
Pre-DPO: Improving Data Utilization in Direct Preference Optimization Using a Guiding Reference Model
Junshu Pan, Wei Shen, Shulin Huang +2
Direct Preference Optimization (DPO) simplifies reinforcement learning from human feedback (RLHF) for large language models (LLMs) by directly optimizing human preferences without…
Beyond English-Centric Training: How Reinforcement Learning Improves Cross-Lingual Reasoning in LLMs
Shulin Huang, Yiran Ding, Junshu Pan +1
Enhancing the complex reasoning capabilities of Large Language Models (LLMs) attracts widespread attention. While reinforcement learning (RL) has shown superior performance for imp…
How Far Are AI Scientists from Changing the World?
Qiujie Xie, Yixuan Weng, Minjun Zhu +9
The emergence of large language models (LLMs) is propelling automated scientific discovery to the next level, with LLM-based Artificial Intelligence (AI) Scientist systems now taki…
MCEval: A Dynamic Framework for Fair Multilingual Cultural Evaluation of LLMs
Shulin Huang, Linyi Yang, Yue Zhang
Large language models exhibit cultural biases and limited cross-cultural understanding capabilities, particularly when serving diverse global user populations. We propose MCEval, a…
ThinkBench: Dynamic Out-of-Distribution Evaluation for Robust LLM Reasoning
Shulin Huang, Linyi Yang, Yan Song +9
Evaluating large language models (LLMs) poses significant challenges, particularly due to issues of data contamination and the leakage of correct answers. To address these challeng…