Dr. Lingyong Yan

Dr. Lingyong Yan

Staff Engineer in Baidu Search Strategy Department, Baidu Inc.

Lingyong Yan is currently a Staff Engineer in Deep QA Team at Baidu Inc. Before that, he recieved the Ph.D. degree in Institute of Software, Chinese Academy of Sciences (ISCAS) under the supervisor of Professor Sun Le. Early, he got his bachelor degree in Software Engineering from Huazhong University of Science and Technology. He has a broad interest in several research areas, including Natural Lanuge Processing, Information Retrieval, Large Language Models, etc.

Research Interests

  • Large Language Model and Generative Retrieval
  • Reinforcement Learning and Multi-agent Cooperation
  • Information Extraction & Knowledge Graph

Education

  • B.S. in Huazhong University of Science and Technology, China. (2010 - 2014)
  • M.S. & Ph.D. in Chines Information Process Lab, ISCAS. (2014 – 2021)

Recent Publications

  • Yukun Zhao, Lingyong Yan, Weiwei Sun, Guoliang Xing, Chong Meng, Shuaiqiang Wang, Zhicong Cheng, Zhaochun Ren and Dawei Yin. 2024. Knowing What LLMs DO NOT Know: A Simple Yet Effective Self-Detection Method. Accepted to NAACL 2024.
  • Yukun Zhao, Lingyong Yan, Weiwei Sun, Guoliang Xing, Shuaiqiang Wang, Chong Meng, Zhicong Cheng, Zhaochun Ren and Dawei Yin. 2024. Improving the Robustness of Large Language Models via Consistency Alignment. Accepted to LREC-COLING 2024.
  • Weiwei Sun, Lingyong Yan, Xinyu Ma, Shuaiqiang Wang, Pengjie Ren, Zhumin Chen, Dawei Yin, Zhaochun Ren. Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents. Accepted to EMNLP 2023.
  • Yukun Zhao*, Lingyong Yan*(co-first author), Weiwei Sun, Chong Meng, Shuaiqiang Wang, Zhicong Cheng, Zhaochun Ren, Dawei Yin. DiQAD: A Benchmark Dataset for Open-domain Dialogue Quality Assessment. Accepted to Findings of EMNLP 2023.
  • Weiwei Sun, Lingyong Yan, Zheng Chen, Shuaiqiang Wang, Haichao Zhu, Pengjie Ren, Zhumin Chen, Dawei Yin, Maarten de Rijke, Zhaochun Ren. Learning to Tokenize for Generative Retrieval. Accepted to NeurIPS 2023.
  • Lingyong Yan, Xianpei Han and Le Sun. Progressive Adversarial Learning for Bootstrapping: A Case Study on Entity Set Expansion. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP2021). (paper, code)
  • Fangchao Liu, Lingyong Yan, Hongyu Lin, Xianpei Han, Le Sun. Element Intervention for Open Relation Extraction. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL 2021).
  • Boxi Cao, Hongyu Lin, Xianpei Han, Le Sun, Lingyong Yan, Meng Liao, Tong Xue, Jin Xu. Knowledgeable or Educated Guess: Rethinking Masked Language Models as Factual Knowledge Bases. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL 2021).

Academic Committees

  • Reviewer: ACL, EMNLP, NAACL, AAAI, WWW, TKDE.