Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
SciCustom: A Framework for Custom Evaluation of Scientific Capabilities in Large Language Models
Yiyang Gu, Junwei Yang, Junyu Luo +15
Large language models (LLMs) are increasingly applied to scientific research, yet existing evaluations often fail to reflect the fine-grained capabilities required in practice. Mos…
cs.CL2025
ExLM: Rethinking the Impact of [MASK] Tokens in Masked Language Models
Kangjie Zheng, Junwei Yang, Siyue Liang +5
Masked Language Models (MLMs) have achieved remarkable success in many self-supervised representation learning tasks. MLMs are trained by randomly masking portions of the input seq…