Dongfang Li (李东方)
Ph.D.
lidongfang AT hit.edu.cn
Harbin Institute of Technology (Shenzhen)
Shenzhen, Guangdong, China
[Google Scholar] [Semantic Scholar] [CV] [Reading List] [Github]

Biography

I am currently a postdoctoral research fellow at Harbin Institute of Technology (Shenzhen) under the guidance of Prof. Min Zhang and Prof. Aiguo Wu. My current research interests focus on Natural Language Processing, Interpretability, Large Language Models, Trustworthy ML.

[Collaboration or Mentorship - 合作实习生,欢迎有意向的伙伴联系(长期有效)] If you would like to collaborate with me, or if you need my mentorship for your research projects, feel free to reach out !

News

  • [2024-09] Two papers are accepted by NeurIPS 2024.
  • [2024-09] Four papers are accepted by EMNLP 2024.
  • [2024-06] Serving as Area Chair for EMNLP 2024.
  • [2024-05] Two papers are accepted by ACL 2024 and ACL Findings.
  • [2024-02] One paper is accepted by LREC-COLING 2024.
  • [2023-12] One paper is accepted by AAAI 2024.
  • [2023-10] Serving as Area Chair of ACL Rolling Reviewer (ARR).
  • [2023-10] One paper is accepted by EMNLP 2023 - Findings.
  • [2023-07] Serving as Co-chair of IJCNLP-AACL (Student Research Workshop) 2023.
  • [2023-05] One paper is accepted by ACL 2023 TrustNLP workshop.
  • [2023-03] LLM Reading List - A paper & resource list of large language models.
  • [2022-12] I gave a talk about my works at SAAI.
  • [2022-10] I gave a talk about my works at Baidu.
  • [2022-10] One paper is accepted by EMNLP 2022 (Short, 12% acceptance rate).
  • [2022-08] One paper is accepted by COLING 2022 (24.2% acceptance rate).
  • [2022-08] We won the first place in CCKS 2022: NL2SQL for Financial-based TableQA.
  • [2022-08] We got the second place in Language And Intelligence Challenge.
  • [2022-06] Review invitation by 3 areas: "Interpretability", "NLP Applications" and "Information Extraction" for EMNLP 2022.
  • [2022-05] I gave a talk about my works at AI TIME PhD-AAAI.
  • [2021-12] Two papers are accepted by AAAI 2022 (15% acceptance rate).
  • [2020-12] I gave a talk about my works at CSSNLP 2020.
  • [2020-10] One papers is accepted by KBS journal.
  • [2020-09] One paper is accepted by EMNLP 2020.
  • Selected Publications

  • Dongfang Li, Xinshuo Hu, Zetian Sun, Baotian Hu, Shaolin Ye, Zifei Shan, Qian Chen, Min Zhang. TruthReader: Towards Trustworthy Document Assistant Chatbot with Reliable Attribution. The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP) System Demonstration Track.
  • Dongfang Li, zhenyu liu, Xinshuo Hu, Zetian Sun, Baotian Hu, Min Zhang. In-Context Learning State Vector with Inner and Momentum Optimization. The Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS), 2024.
  • Dongfang Li, Zetian Sun, Baotian Hu, zhenyu liu, Xinshuo Hu, Xuebo Liu, Min Zhang. Improving Attributed Text Generation of Large Language Models via Preference Learning. The 62nd Annual Meeting of the Association for Computational Linguistics (ACL): Findings, 2024.
  • Ziyang Chen*, Dongfang Li*, Xiang Zhao, Baotian Hu, Min Zhang. Temporal Knowledge Question Answering via Abstract Reasoning Induction. The 62nd Annual Meeting of the Association for Computational Linguistics (ACL), 2024.
  • Xinshuo Hu*, Dongfang Li*, Baotian Hu, Zihao Zheng, Zhenyu Liu, Min Zhang. Separate the Wheat from the Chaff: Model Deficiency Unlearning via Parameter-Efficient Module Operation. Proceedings of the 38th AAAI Conference on Artificial Intelligence (AAAI), 2024.
  • Dongfang Li, Jindi Yu, Baotian Hu, Zhenran Xu, Min Zhang. ExplainCPE: A Free-text Explanation Benchmark of Chinese Pharmacist Examination. Proceedings of the 2023 conference on Empirical Methods in Natural Language Processing (EMNLP): Findings, 2023.
  • Dongfang Li, Baotian Hu, Qingcai Chen, Tujie Xu, Jingcong Tao, Yunan Zhang. Unifying Model Explainability and Robustness for Joint Text Classification and Rationale Extraction. Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI), 2022, 36(10), 10947-10955. (Oral)
  • Junying Chen*, Dongfang Li*, Qingcai Chen, Wenxiu Zhou, Xin Liu. Diaformer: Automatic Diagnosis via Symptoms Sequence Generation. Proceedings of the AAAI Conference on Artificial Intelligence (AAAI). 2022, 36(4): 4432-4440. (* = equal contribution)
  • Dongfang Li, Baotian Hu, Qingcai Chen. Calibration Meets Explanation: A Simple and Effective Approach for Model Confidence Estimates. Proceedings of the 2022 conference on Empirical Methods in Natural Language Processing (EMNLP), 2022, 2775–2784.
  • Dongfang Li, Baotian Hu, Qingcai Chen. Prompt-based Text Entailment for Low-Resource Named Entity Recognition. Proceedings of the 29th International Conference on Computational Linguistics (COLING), 2022, 1896-1903.
  • Dongfang Li, Baotian Hu, Qingcai Chen, Xiao Wang, Quanchang Qi, Liubin Wang, Haishan Liu. Attentive Capsule Network for Click-through Rate and Conversion Rate Prediction in Online Advertising. Knowledge-based Systems (KBS), 2021, 212: 106611.
  • Dongfang Li, Baotian Hu, Qingcai Chen, Weihua Peng, Anqi Wang. Towards Medical Machine Reading Comprehension with Structural Knowledge and Plain Text. Proceedings of the 2020 conference on Empirical Methods in Natural Language Processing (EMNLP), 2020, 1427-1438.
  • Experiences

    Academic Services

    • Co-chair of IJCNLP-AACL (Student Research Workshop) 2023, ACL Rolling Reviewer (ARR) / NAACL / EMNLP - Area Chair
    • Journal Reviewer: IEEE Transactions on Neural Networks and Learning Systems, Knowledge-Based Systems, Applied Intelligence, Neural Processing Letters
    • Conference Reviewer: COLM 2024, ICLR 2024, 2025, ACL 2021-, EMNLP 2020-, EACL 2023, AACL-IJCNLP 2022, AAAI 2023, IJCAI 2023-, CCKS 2021-, NLPCC 2021-, COLING 2020-, CCL 2021-, NAACL 2022-, ACL Rolling Review
    • Workshop Reviewer: Instruction Workshop@NeurIPS 2023, MATH-AI Workshop@NeurIPS 2023, TrustNLP 2024 Committee, SET LLM@ICLR 2024, ME-FoMo@ICLR 2024, WiNLP@EMNLP 2024

    Industrial Projects

    • Baidu's complex knowledge graph project in the medical field
    • Tencent's intelligent dialogue and marketing transformation (CTR/CVR)
    • QA projects of WeBank, China CITIC Bank, and China Merchants Bank
    • Harbin Institute of Technology (Shenzhen)-Tencent Artificial Intelligence Laboratory Team Leader: Intelligent Customer Service
    • Harbin Institute of Technology (Shenzhen)-Turing Robotics Joint Laboratory Team Leader (15+ members): Financial Information Extraction, Text Comparison, Contract Review, Smart Investment Projects (e.g., Industry Chain KG), Smart Financial Information Mining