3 papers
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
o-MEGA: Optimized Methods for Explanation Generation and Analysis
Ľuboš Kriš, Jaroslav Kopčan, Qiwei Peng +3
The proliferation of transformer-based language models has revolutionized NLP domain while simultaneously introduced significant challenges regarding model transparency and trustwo…
cs.CL2025
Investigating Language and Retrieval Bias in Multilingual Previously Fact-Checked Claim Detection
Ivan Vykopal, Antonia Karamolegkou, Jaroslav Kopčan +4
Multilingual Large Language Models (LLMs) offer powerful capabilities for cross-lingual fact-checking. However, these models often exhibit language bias, performing disproportionat…