@inproceedings{chen-etal-2026-token,
    title = "Token-level Inference-Time Alignment for Vision-Language Models",
    author = "Chen, Kejia  and
      Zheng, Junjun  and
      Zhang, Jiawen  and
      Lin, Manxi  and
      Pan, Xiao  and
      Hu, Jiacong  and
      Lou, Jian  and
      Feng, Zunlei  and
      Song, Mingli",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1253/",
    pages = "25012--25029",
    ISBN = "979-8-89176-395-1",
    abstract = "Vision-Language Models (VLMs) often prioritize linguistic fluency over visual fidelity, leading to hallucinations where generated text contradicts the image. Countering this bias typically requires resource-heavy fine-tuning or high-latency verification methods that provide feedback only after the full response is generated. To overcome these limitations, we present a framework for Token-level Inference-Time Alignment (TITA) that steers the decoding process without updating the base model parameters. By training a lightweight reward model to capture visual preferences, TITA extracts implicit guidance through log-probability ratios. This approach functions as an inference-time adaptation of Direct Preference Optimization (DPO), injecting dense feedback to correct the output distribution at every generation step. Across diverse architectures including LLaVA-1.5, Qwen3-VL, and InternVL3.5, TITA consistently improves performance on 13 benchmarks. For example, TITA boosts LLaVA-1.5-7B by 8.6{\%} on MMVet and achieves a 74.0 MMStar score with Qwen3-VL-8B. Specifically, these gains incur negligible overhead ({\textasciitilde}0.2s per query), offering a superior trade-off between alignment effectiveness and efficiency. Our code is available at: https://github.com/Thecommonirin/TITA."
}