Zhicheng YANG

Zhicheng YANG

Reasoning with LLMs

Short Bio

Bro is currently pursuing a PhD degree with a keen focus on Reasoning with Large Language Models (LLMs). I focus on the following topics:

  • LLM Reasoning (with or without verifiable reward)
  • Reasoning Data Synthesis
  • Test-Time Scaling

If you’re interested in collaborating or exploring potential research opportunities, please don’t hesitate to reach out (带带哥们).

News

Preprints

🔥Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with Adaptive Exploration
Zhicheng Yang, Zhijiang Guo, Yinya Huang, Yongxin Wang, Dongchun Xie, Yiwei Wang, Xiaodan Liang, Jing Tang
[Paper] [Code]

Critique to Verify: Accurate and Honest Test-Time Scaling with RL-Trained Verifiers
Zhicheng Yang, Zhijiang Guo, Yinya Huang, Yongxin Wang, Yiwei Wang, Xiaodan Liang, Jing Tang
[Paper] [Code]

TreeRPO: Tree Relative Policy Optimization
Zhicheng Yang, Zhijiang Guo, Yinya Huang, Yongxin Wang, Yiwei Wang, Xiaodan Liang, Jing Tang
[Paper] [Code]

Selected Publication

OptiBench Meets ReSocratic: Measure and Improve LLMs for Optimization Modeling
Zhicheng Yang, Yiwei Wang, Yinya Huang, Zhijiang Guo, Wei Shi, Xiongwei Han, Liang Feng, Linqi Song, Xiaodan Liang, Jing Tang
The Thirteenth International Conference on Learning Representations (ICLR 2025)
[Paper] [Code]

AlignedCoT: Prompting Large Language Models via Native-Speaking Demonstrations
Zhicheng Yang, Yinya Huang, Jing Xiong, Liang Feng, Xiaodan Liang, Yiwei Wang, Jing Tang
The 2024 Conference on Empirical Methods in Natural Language Processing. (Findings of EMNLP 2024)
[Paper] [Code]

LogicSolver: Towards Interpretable Math Word Problem Solving with Logical Prompt-enhanced Learning
Zhicheng Yang*, Jinghui Qin*, Jiaqi Chen, Liang Lin, Xiaodan Liang
The 2022 Conference on Empirical Methods in Natural Language Processing. (Findings of EMNLP 2022)
[Paper] [Code]

Unbiased Math Word Problems Benchmark for Mitigating Solving Bias
Zhicheng Yang, Jinghui Qin, Jiaqi Chen, Xiaodan Liang
Annual Conference of the North American Chapter of the Association for Computational Linguistics, 2022. (Findings of NAACL 2022)
[Paper] [Code]

CLOMO: Counterfactual Logical Modification with Large Language Models
Yinya Huang, Ruixin Hong, Hongming Zhang, Wei Shao, Zhicheng Yang, Dong Yu, Changshui Zhang, Xiaodan Liang, Linqi Song
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics. (ACL 2024)
[Paper]

DQ-LoRe: Dual Queries with Low Rank Approximation Re-ranking for In-Context Learning
Jing Xiong, Zixuan Li, Chuanyang Zheng, Zhijiang Guo, Yichun Yin, Enze Xie, Zhicheng Yang, Qingxing Cao, Haiming Wang, Xiongwei Han, Jing Tang, Chengming Li, Xiaodan Liang
12th International Conference on Learning Representations, 2024. (ICLR 2024)
[Paper]

ATG: Benchmarking Automated Theorem Generation for Generative Language Models
Xiaohan Lin, Qingxing Cao, Yinya Huang, Zhicheng Yang, Zhengying Liu, Zhenguo Li, Xiaodan Liang
Annual Conference of the North American Chapter of the Association for Computational Linguistics, 2024. (Findings of NAACL 2024)
[Paper]

Template-based Contrastive Distillation Pre-training for Math Word Problem Solving
Jinghui Qin*, Zhicheng Yang*, Jiaqi Chen, Xiaodan Liang and Liang Lin
IEEE Transactions on Neural Networks and Learning Systems, 2023. (TNNLS)
[Paper]

(* denotes co-first authors)

Education

  • 2020 — 2023: Master in Pattern Recognition and Intelligent Systems, Sun Yat-sen University (Shenzhen)
  • 2016 — 2020: B.Sc. in Computer Science and Technology, Sun Yat-sen University (Panyu)

Honors and Awards

  • National First Prize, Contemporary Undergraduate Mathematical Contest in Modeling (CUMCM), China
  • First Prize Scholarship, Sun Yat-sen University

Experience

  • LLM Research Intern, ByteDance-Seed
  • NLP Research Intern, Huawei Noah's Ark
  • Recommender System Intern, ByteDance-Data-Douyin
  • NLP Research Intern, DMAI

Flag Counter