Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
Distribution-aware Language Neuron Identification in Multilingual Large Language Models
Minjun Kim, Inho Won, Junghun Yuk +3
Multilingual large language models (mLLMs) contain a small fraction of feed-forward neurons that are sensitive to particular languages, commonly termed language-specific neurons. E…
cs.CL2026
Hidden Threat in Synthetic Data: Covert Targeted Bias Injection through Benign Text
Minkyung Cho, Jihyo Kim, SeungWoo Song +4
Synthetic data is increasingly used to train large language models (LLMs), yet its security implications remain poorly understood. Prior work on subliminal learning suggests that m…