Decoy Direction Optimization: A Post-Hoc Defense Against LLM Abliteration
Paper • 2609.16204 • Published • 4
AI & ML interests
None defined yet.
Recent Activity
View all activity
aashiqmuhamed
authored 5
papers about 1 month ago
Pick Your Poison: Learning to Select Poison Sets for Stronger LLM Backdoor Attacks
Paper • 2609.15029 • Published • 8
MOLE: Detecting Insider Threats in AI Agents
Paper • 2609.06966 • Published • 18
Beyond Understanding: Evaluating the Pragmatic Gap in LLMs' Cultural Processing of Figurative Language
Paper • 2510.23828 • Published • 2
RefusalBench: Generative Evaluation of Selective Refusal in Grounded Language Models
Paper • 2510.10390 • Published • 5
aashiqmuhamed
submitted 2
papers to Daily Papers about 1 month ago
aashiqmuhamed
updated a
dataset about 1 month ago
aashiqmuhamed
submitted a
paper to Daily Papers about 1 month ago
aashiqmuhamed
published a
dataset about 1 month ago
stevenkolawole
updated a
dataset about 1 year ago
gingsmith
authored a
paper over 1 year ago
aashiqmuhamed
authored 3
papers over 1 year ago
SAEs $\textit{Can}$ Improve Unlearning: Dynamic Sparse Autoencoder Guardrails for Precision Unlearning in LLMs
Paper • 2504.08192 • Published • 3
CoRAG: Collaborative Retrieval-Augmented Generation
Paper • 2504.01883 • Published • 9
Position: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEs
Paper • 2505.20254 • Published • 5
neilkale
updated a
dataset over 1 year ago
stevenkolawole
published a
dataset over 1 year ago
neilkale
updated a
dataset over 1 year ago
neilkale
published a
dataset over 1 year ago
neilkale
updated a
dataset over 1 year ago