Soumyadeep Pal

Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model Outputs

Leak@$k$: Unlearning Does Not Make LLMs Forget Under Probabilistic Decoding

LLM Unlearning Under the Microscope: A Full-Stack View on Methods and Metrics

Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning

LLM Unlearning Reveals a Stronger-Than-Expected Coreset Effect in Current Benchmarks