I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders
Paper
•
2503.18878
•
Published
•
119
Oleg Y. Rogov
qubitter
AI & ML interests
Adversarial ML
Recent Activity
upvoted
a
paper
18 days ago
When Models Lie, We Learn: Multilingual Span-Level Hallucination
Detection with PsiloQA
Organizations
authored
6
papers
2 months ago
Geopolitical biases in LLMs: what are the "good" and the "bad" countries according to contemporary language models
Paper
•
2506.06751
•
Published
•
71
AASIST3: KAN-Enhanced AASIST Speech Deepfake Detection using SSL Features and Additional Regularization for the ASVspoof 2024 Challenge
Paper
•
2408.17352
•
Published
•
1
Speech-to-LaTeX: New Models and Datasets for Converting Spoken Equations and Sentences
Paper
•
2508.03542
•
Published
•
4
Certification of Speaker Recognition Models to Additive Perturbations
Paper
•
2404.18791
•
Published
Novel Loss-Enhanced Universal Adversarial Patches for Sustainable Speaker Privacy
Paper
•
2505.19951
•
Published
authored
a
paper
about 1 year ago