Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
Not X, but When: Diagnosing a Mandarin LLM Writing Tic through Contextual Appropriateness
Yihang Peng, Yi Jing, Dewen Liu +2
Recurring expressions in model-written text are often treated as signatures of machine authorship, yet most of them serve legitimate functions. Whether such an expression is a tic…
cs.CL2026
SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization
Weihan Meng, Hongzhu Guo, Yi Jing +5
Sparse autoencoders (SAEs) are proposed to extract numerous features from large language model (LLM) representations, yet explaining these features still relies primarily on extern…