4 papers
Evaluating Adjective-Noun Compositionality in LLMs: Functional vs Representational Perspectives
Ruchira Dhar, Qiwei Peng, Anders Søgaard
Compositionality is considered central to language abilities. As performant language systems, how do large language models (LLMs) do on compositional tasks? We evaluate adjective-n…
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…
o-MEGA: Optimized Methods for Explanation Generation and Analysis
ĽuboÅ¡ KriÅ¡, Jaroslav KopÄan, Qiwei Peng +3
The proliferation of transformer-based language models has revolutionized NLP domain while simultaneously introduced significant challenges regarding model transparency and trustwo…
Investigating Language and Retrieval Bias in Multilingual Previously Fact-Checked Claim Detection
Ivan Vykopal, Antonia Karamolegkou, Jaroslav KopÄan +4
Multilingual Large Language Models (LLMs) offer powerful capabilities for cross-lingual fact-checking. However, these models often exhibit language bias, performing disproportionat…