2 papers
cs.CL2026
The Tatoxa System for Text Detoxification in Low-Resource Languages: The Case of Tatar
Ilseyar Alimova, Bogdan Monogov, Artyom Mazur +5
Text detoxification, the automated detection and mitigation of abusive and harmful content, is essential for ensuring the safety of online communities and protecting users. However…
cs.CV2026
DifFRACT: Diffusion Feature Reconstruction and Attribution for Circuit Tracing
Artyom Mazur, Nina Konovalova, Aibek Alanov
Mechanistic interpretability seeks to explain neural network behavior by decomposing model computations into interpretable features and circuits. While transcoder-based circuit tra…