Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
What Gets Activated: Uncovering Domain and Driver Experts in MoE Language Models
Guimin Hu, Meng Li, Qiwei Peng +3
Most interpretability work focuses on layer- or neuron-level mechanisms in Transformers, leaving expert-level behavior in MoE LLMs underexplored. Motivated by functional specializa…
cs.CL2025
Debiasing Multilingual LLMs in Cross-lingual Latent Space
Qiwei Peng, Guimin Hu, Yekun Chai +1
Debiasing techniques such as SentDebias aim to reduce bias in large language models (LLMs). Previous studies have evaluated their cross-lingual transferability by directly applying…