Yan Meng
PhD researcher in NLP · University of Amsterdam
I study multilingual knowledge transfer, reasoning, and translation for language models.
- COLM 2025 Control the Temperature: Selective Sampling for Diverse and High-Quality LLM Outputs
- NAACL Findings 2025 How to Learn in a Noisy World? Self-Correcting the Real-World Data Noise on Machine Translation
- EACL 2024 Disentangling the Roles of Target-side Transfer and Regularization in Multilingual Machine Translation
- IJCNLP-AACL 2023 FollowupQG: Towards Information-Seeking Followup Question Generation
- Jul 11, 2025 How Does Decoding Affect Reasoning in LLMs? Greedy decoding is accurate but repetitive; sampling is diverse but risky. Selective sampling switches between the two at each decoding position to get both.