| Mitigating the Alignment Tax of RLHF Y Lin, H Lin, W Xiong, S Diao, J Liu, J Zhang, R Pan, H Wang, W Hu, ... EMNLP-2024, 2023 | 225* | 2023 |
| R-Tuning: Instructing Large Language Models to Say ‘I Don’t Know’ H Zhang, S Diao, Y Lin, Y Fung, Q Lian, X Wang, Y Chen, H Ji, T Zhang NAACL-2024 (Outstanding Paper Award), 7106-7132, 2024 | 191* | 2024 |
| Entropy-regularized process reward model H Zhang, P Wang, S Diao, Y Lin, R Pan, H Dong, D Zhang, P Molchanov, ... Transactions on Machine Learning Research (TMLR), 2024 | 63* | 2024 |
| Self-rewarding correction for mathematical reasoning W Xiong, H Zhang, C Ye, L Chen, N Jiang, T Zhang arXiv preprint arXiv:2502.19613, 2025 | 41 | 2025 |
| ScaleBiO: Scalable Bilevel Optimization for LLM Data Reweighting R Pan, D Zhang, H Zhang, X Pan, M Xu, J Zhang, R Pi, X Wang, T Zhang ACL-2025, 2024 | 35* | 2024 |
| Online-dpo-r1: Unlocking effective reasoning without the ppo overhead, 2025 H Zhang, J Yao, C Ye, W Xiong, T Zhang Notion Blog, 2025 | 18* | 2025 |
| Optimizing Chain-of-Thought Reasoners via Gradient Variance Minimization in Rejection Sampling and RL J Yao, Y Hao, H Zhang, H Dong, W Xiong, N Jiang, T Zhang NeurIPS-2025, 2025 | 6 | 2025 |
| RAG-Reward: Optimizing RAG with Reward Modeling and RLHF H Zhang, J Song, J Zhu, Y Wu, T Zhang, C Niu arXiv preprint arXiv:2501.13264, 2025 | 6 | 2025 |
| Understanding Overadaptation in Supervised Fine-Tuning: The Role of Ensemble Methods Y Hao, X Pan, H Zhang, C Ye, R Pan, T Zhang ICML-2025, 2025 | 4 | 2025 |
| DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning Y Wu, J Song, H Zhang, T Zhang, C Niu arXiv preprint arXiv:2506.17533, 2025 | | 2025 |
| Towards Better Generalization via Distributional Input Projection Network Y Hao, Y Lu, H Zhang, X Shen, T Zhang arXiv preprint arXiv:2506.04690, 2025 | | 2025 |
| InfoPattern: Unveiling Information Propagation Patterns in Social Media C Han, J Xu, M Li, H Zhang, T Abdelzaher, H Ji arXiv preprint arXiv:2311.15642, 2023 | | 2023 |
Tong ZhangUIUCVerified email at tongzhang-ml.org
