@inproceedings{weng-etal-2026-finesteer,
    title = "{F}ine{S}teer: A Unified Framework for Fine-Grained Inference-Time Steering in Large Language Models",
    author = "Weng, Zixuan  and
      Zhang, Jinghuai  and
      Cai, Kunlin  and
      Li, Ying  and
      Wang, Peiran  and
      Tian, Yuan",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.852/",
    pages = "18736--18756",
    ISBN = "979-8-89176-390-6",
    abstract = "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 training-efficient due to their rigid, one-size-fits-all designs and limited adaptability. In this work, we present FineSteer, a novel steering framework that decomposes inference-time steering into two complementary stages{---}conditional steering and fine-grained vector synthesis{---}allowing fine-grained control over when and how to steer internal representations. In the first stage, we introduce a Subspace-guided Conditional Steering (SCS) mechanism that preserves model utility by avoiding unnecessary steering. In the second stage, we propose a Mixture-of-Steering-Experts (MoSE) mechanism that captures the multimodal nature of desired steering behaviors and generates query-specific steering vectors for improved effectiveness. Through tailored designs in both SCS and MoSE, FineSteer maintains robust performance on general queries while adaptively optimizing steering vectors for targeted inputs in a training-efficient manner. Extensive experiments on safety and truthfulness benchmarks show that FineSteer outperforms the state-of-the-art methods in overall performance (e.g., a 7.6{\%} improvement on TruthfulQA over Llama-3), achieving stronger steering performance with minimal utility loss. The code is available at https://github.com/YukinoAsuna/FineSteer"
}