FineSteer: A Unified Framework for Fine-Grained Inference-Time Steering in Large Language Models

ArXi:2604.15488v1 Announce Type: cross Large language models (LLMs) often exhibit undesirable behaviors, such as safety violations and hallucinations. Although inference-time steering offers a cost-effective way to adjust model behavior without updating its parameters, existing methods often fail to be simultaneously effective, utility-preserving, and