avatar

Weixiang Yan

颜为骧

Applied Scientist@Amazon
yanweixiang.ywx (at) gmail.com
California, USA


I am an applied scientist at the Amazon Generative Foundation Modeling Team, focusing on hallucination and reasoning. Previously, I obtained a Master's degree in Computer Science from the University of California, Santa Barbara, and received dual bachelor's degrees in engineering and management from Beijing University of Posts and Telecommunications. Broadly, my research interests are in the area of code intelligence, NLP, and software automation. I was a research intern at Microsoft Research Asia and Alibaba DAMO Academy. At the same time, I am a member of the BigCode🤗 team, an open-source team for intelligent coding.

Publications ( * denotes equal contribution)

    2024

  1. ClinicalLab: Aligning Agents for Multi-Departmental Clinical Diagnostics in the Real World
    Weixiang Yan, Haitian Liu, Tengxiao Wu, Qian Chen, Wen Wang, Haoyuan Chai, Jiayi Wang, Weishan Zhao, Yixin Zhang, Renjun Zhang, Li Zhu, Xuandong Zhao, Xifeng Yan
    arXiv PDF Code Data
  2. CodeHalu: Investigating Code Hallucinations in LLMs via Execution-based Verification
    Yuchen Tian*, Weixiang Yan*, Qian Yang, Xuandong Zhao, Qian Chen, Wen Wang, Ziyang Luo, Lei Ma, Dawn Song
    The 39th Annual AAAI Conference on Artificial Intelligence
    AAAI PDF Code Data
  3. Decompose and Compare Consistency: Measuring VLMs' Answer Reliability via Task-Decomposition Consistency Comparison
    Qian Yang, Weixiang Yan, Aishwarya Agrawal
    Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
    EMNLP PDF
  4. CodeJudge-Eval: Can Large Language Models be Good Judges in Code Understanding?
    Yuwei Zhao, Ziyang Luo, Yuchen Tian, Hongzhan Lin, Weixiang Yan, Annan Li, Jing Ma
    The 31st International Conference on Computational Linguistics
    COLING PDF Code Data

    5. 2023

  5. CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and Generation
    Weixiang Yan, Haitian Liu, Yunkun Wang, Yunzhe Li, Qian Chen, Wen Wang, Tingyu Lin, Weishan Zhao, Li Zhu, Hari Sundaram, Shuiguang Deng
    Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics, 2024.
    ACL PDF Code Data Website Poster Slides
  6. CodeTransOcean: A Comprehensive Multilingual Benchmark for Code Translation
    Weixiang Yan, Yuchen Tian, Yunzhe Li, Qian Chen, Wen Wang
    Findings of the Association for Computational Linguistics: EMNLP 2023.
    EMNLP PDF Code Data Website
  7. Advancing Precise Outline-Conditioned Text Generation with Task Duality and Explicit Outline Control
    Yunzhe Li, Qian Chen, Weixiang Yan, Wen Wang, Qinglin Zhang, Hari Sundaram
    Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics, 2024.
    EACL PDF Code

    8. ~2022

  8. WhyGen: Explaining ML-powered Code Generation by Referring to Training Examples
    Weixiang Yan, Yuanchun Li
    Proceedings of the ACM/IEEE 44th International Conference on Software Engineering Demo Track, 2022.
    ICSE PDF Code Data Video
  9. Dependency-aware form understanding
    Shaokun Zhang, Yuanchun Li, Weixiang Yan, Yao Guo, Xiangqun Chen
    IEEE 32nd International Symposium on Software Reliability Engineering, 2021.
    ISSRE PDF Code
  10. Method for generating text abstract, method and device for training abstract generation model
    Weixiang Yan, Qian Chen, Wen Wang, Qinglin Zhang
    Chinese Patent CN116186244A
    Patents PDF

Services

Educations

Internships