一作ACL 2026Poster· Natural Language Processing
F ine S teer: A Unified Framework for Fine-Grained Inference-Time Steering in Large Language Models
Zixuan Weng · Jinghuai Zhang · Kunlin Cai · Ying Li · Peiran Wang · Yuan Tian
摘要
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, utilit...