🔭 Publications
- TRACE: An Evidence-Grounded Benchmark for Safety Evaluation of Large Reasoning Models. by Z. Wu, et al. EMNLP, 2026. DDL 2.0@ IJCAI, 2026.
- Enhancing Mathematical Reasoning in LLMs by Stepwise Correction by Z. Wu, et al. ACL, 2025.
- Large Language Models Can Self-Correct with Key Condition Verification by Z. Wu, et al. EMNLP, 2024. AI4MATH@ICML, 2024.
- Instructing Large Language Models to Identify and Ignore Irrelevant Conditions by Z. Wu, C. Shen, M. Jiang. NAACL, 2024.
- Get an A in Math: Progressive Rectification Prompting by Z. Wu, M. Jiang, C. Shen. AAAI, 2024.


