publications

2024

  1. Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge
    Tianhao Wu, Weizhe Yuan, Olga Golovneva , and 5 more authors
    arXiv preprint arXiv:2407.19594, 2024
  2. From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline
    Tianle Li, Wei-Lin Chiang, Evan Frick , and 5 more authors
    arXiv preprint arXiv:2406.11939, 2024
  3. RouteLLM: Learning to Route LLMs with Preference Data
    Isaac Ong, Amjad Almahairi, Vincent Wu , and 5 more authors
    arXiv preprint arXiv:2406.18665, 2024

2023

  1. starling.png
    Starling-7B: Improving LLM Helpfulness & Harmlessness with RLAIF
    Banghua Zhu, Evan Frick, Tianhao Wu , and 2 more authors
    Nov 2023
  2. Statistical Inference on Multi-armed Bandits with Delayed Feedback
    Lei Shi, Jingshen Wang, and Tianhao Wu
    Nov 2023
  3. A Reduction-based Framework for Sequential Decision Making with Delayed Feedback
    Yunchang Yang, Han Zhong, Tianhao Wu , and 3 more authors
    arXiv preprint arXiv:2302.01477, Nov 2023
  4. Pairwise Proximal Policy Optimization: Harnessing Relative Feedback for LLM Alignment
    Tianhao Wu, Banghua Zhu, Ruoyu Zhang , and 3 more authors
    Nov 2023

2022

  1. Nearly optimal policy optimization with stable at any time guarantee
    Tianhao Wu, Yunchang Yang, Han Zhong , and 3 more authors
    In International Conference on Machine Learning , Nov 2022

2021

  1. On reinforcement learning with adversarial corruption and its application to block mdp
    Tianhao Wu, Yunchang Yang, Simon Du , and 1 more author
    In International Conference on Machine Learning , Nov 2021
  2. A unified framework for conservative exploration
    Yunchang Yang, Tianhao Wu, Han Zhong , and 5 more authors
    arXiv preprint arXiv:2106.11692, Nov 2021

2020

  1. Sanity-checking pruning methods: Random tickets can win the jackpot
    Jingtong Su, Yihang Chen, Tianle Cai , and 4 more authors
    Advances in neural information processing systems, Nov 2020