4 papers
SafeTune: A Unified Faithful Library for Auditing and Repairing Safety Drift in Fine-Tuned LLMs
Pratinav Seth, Saisab Sadhu, Anshul Kaushal +1
Methods for addressing safety drift in fine-tuned Large Language Models (LLMs) are scattered across incompatible implementations, lifecycle stages, and evaluation protocols, making…
What Do Compliance Detectors Read? An Audit of Activation Probes and Guard Models
Saisab Sadhu, Aadit Sengupta, Vinay Kumar Sankarapu +1
Regulatory compliance monitoring in deployed language models is increasingly implemented as a legal and audit control, checking model outputs against written rules spanning data pr…
Forgetting That Sticks: Quantization-Permanent Unlearning via Circuit Attribution
Saisab Sadhu, Pratinav Seth, Vinay Kumar Sankarapu
Standard unlearning evaluations measure behavioral suppression in full precision, immediately after training, despite every deployed language model being quantized first. Recent wo…
Hierarchical Pedagogical Oversight: A Multi-Agent Adversarial Framework for Reliable AI Tutoring
Saisab Sadhu, Ashim Dhor
Large Language Models (LLMs) are increasingly deployed as automated tutors to address educator shortages; however, they often fail at pedagogical reasoning, frequently validating i…