(* equal contribution, full publications can be found in my Google Scholar)

Selected Publications

ACL 2024

• 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
  ACL 2024
  paper / code

ICML 2024 (Oral)

• Do pretrained Transformers Really Learn In-context by Gradient Descent?
  Lingfeng Shen, Aayush Mishra, Daniel Khashabi
  ICML 2024 (Oral)
  paper / code

ICLR 2024

• 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
  ICLR 2024
  paper / code

EMNLP 2022 (Oral)

• On the Evaluation Metrics for Paraphrase Generation
  Lingfeng Shen, Lemao Liu, Haiyun Jiang, Shuming Shi
  EMNLP 2022 (Oral)
  paper / code

Research Experience

• Research Scientist (Current)
  Seed LLM department, Bytedance
  Working on agentic foundation models and emergent behaviors

• 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