Selected PublicationsFull List

  1. ACL'24 / The Language Barrier: Dissecting Safety Challenges of LLMs in Multilingual Contexts
    Lingfeng Shen, Weiting Tan, Sihao Chen, Yunmo Chen, Jingyu Zhang, Haoran Xu, Boyuan Zheng, Philipp Koehn, Daniel Khashabi
    Annual Meeting of the Association for Computational Linguistics (ACL). 2024
    Paper Code
  2. ICML'24 (Oral) / Do Pretrained Transformers Really Learn In-context by Gradient Descent?
    Lingfeng Shen*, Aayush Mishra*, Daniel Khashabi
    International Conference on Machine Learning (ICML). 2024
    Paper Code
  3. ICLR'24 / The Trickle-down Impact of Reward (In-)consistency on RLHF
    Lingfeng Shen, Sihao Chen, Linfeng Song, Lifeng Jin, Baolin Peng, Haitao Mi, Daniel Khashabi, Dong Yu
    International Conference on Learning Representations (ICLR). 2024
    Paper Code
  4. EMNLP'22 (Oral) / On the Evaluation Metrics for Paraphrase Generation
    Lingfeng Shen, Lemao Liu, Haiyun Jiang, Shuming Shi
    Conference on Empirical Methods in Natural Language Processing (EMNLP). 2022
    Paper Code

Research Experience

Member of Technical Staff, MAI SuperIntelligence Team Current

Agentic foundation models.

Research Scientist, Seed LLM Department, ByteDance

Reasoning, planning and function-call capacities of LLMs.

Research Assistant, Johns Hopkins University

Worked with Daniel Khashabi and Philipp Koehn.

Research Intern, Tencent AI Lab

Mentored by Haiyun Jiang, Lemao Liu and Shuming Shi.