Showing cs.CLShow all
3 papers · 1 filter
cs.CL2026
"Not" is Not Lost in Translation: A Causal Analysis of Negation Representations in Multilingual LLMs
Giang Son Nguyen, Wray Buntine, Dung D. Le +1
Negation occurs in every language, yet its surface realization differs drastically. Despite this, multilingual large language models (LLMs) translate negation robustly, raising the…
cs.CL2026
Recurrence Is Not Enough: Causally Validating Multilingual SAE Translation Features in Gemma 2 and 3
Giang Son Nguyen, Nhi Ngoc-Yen Nguyen, Wray Buntine +1
Sparse autoencoder (SAE) features are increasingly used to explain and steer language-model behavior, but it remains unclear whether a feature found in one language context plays t…
cs.CL2026
Scaling Inherently Interpretable Language Models
Guide Labs Team, Andreas Madsen, Aya Abdelsalam Ismail +7
Interpretability is often treated as a tax on capability: language models are trained as opaque systems, then explained after the fact, with methods whose reliability is difficult…