Yan Meng

Yan Meng

PhD researcher in NLP · University of Amsterdam

I study multilingual knowledge transfer, reasoning, and translation for language models.

Google Scholar LinkedIn CV Email

Research Works

Multilingual Knowledge Transfer & Reasoning

arXiv 2026 Do Language Models Reason Across Languages?
EACL 2024 Disentangling the Roles of Target-side Transfer and Regularization in Multilingual Machine Translation

LLM Reasoning & Efficiency

COLM 2025 Control the Temperature: Selective Sampling for Diverse and High-Quality LLM Outputs
ACL 2023 Parameter-Efficient Fine-Tuning without Introducing New Latency

Training Data Quality

NAACL Findings 2025 How to Learn in a Noisy World? Self-Correcting the Real-World Data Noise on Machine Translation
ACL Findings 2024 How Far can 100 Samples Go? Unlocking Zero-Shot Translation with Tiny Multi-Parallel Data

Experiences

Jan – May 2026 Research Intern · WeCo AI Self-Improving Agent

Blog

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.