activity
20242026
collaborators

5 papers

cs.CL2026

CoLD: Counterfactually-Guided Length Debiasing for Process Reward Models in Mathematical Reasoning

Congmin Zheng, Jiachen Zhu, Jianghao Lin +6

Process Reward Models (PRMs) play a central role in evaluating and guiding multi-step reasoning in large language models (LLMs), especially for mathematical problem solving. Howeve…

cs.LG2025

Beyond Markovian: Reflective Exploration via Bayes-Adaptive RL for LLM Reasoning

Shenao Zhang, Yaqing Wang, Yinxiao Liu +5

Large Language Models (LLMs) trained via Reinforcement Learning (RL) have exhibited strong reasoning capabilities and emergent reflective behaviors, such as rethinking and error co…

cs.CV2025

Mitigating Visual Hallucinations via Semantic Curriculum Preference Optimization in MLLMs

Yuanshuai Li, Yuping Yan, Junfeng Tang +3

Multimodal Large Language Models (MLLMs) have significantly improved the performance of various tasks, but continue to suffer from visual hallucinations, a critical issue where gen…

cs.CL2025

Robust Multi-Objective Preference Alignment with Online DPO

Raghav Gupta, Ryan Sullivan, Yunxuan Li +2

Multi-objective preference alignment of large language models (LLMs) is critical for developing AI systems that are more configurable, personalizable, helpful, and safe. However, o…

cs.CL2024

Improve Mathematical Reasoning in Language Models by Automated Process Supervision

Liangchen Luo, Yinxiao Liu, Rosanne Liu +9

Complex multi-step reasoning tasks, such as solving mathematical problems or generating code, remain a significant hurdle for even the most advanced large language models (LLMs). V…