2 papers
cs.LG2026
OPIUM: Mitigating Steering Externalities and Over-Refusal via Dual Objective Latent Optimization
Kavin Aravindan, Arihant Rastogi, Krishak Aneja +4
Activation steering provides a lightweight mechanism for controlling large language models at inference time, but steering vectors can have unintended externalities: utility vector…
cs.CL2026
Intrinsic Guardrails: How Semantic Geometry of Personality Interacts with Emergent Misalignment in LLMs
Krishak Aneja, Manas Mittal, Anmol Goel +2
Fine-tuning Large Language Models (LLMs) on benign narrow data can sometimes induce broad harmful behaviors, a vulnerability termed emergent misalignment (EM). While prior work lin…