@inproceedings{phukan-etal-2025-beyond,
    title = "Beyond Logit Lens: Contextual Embeddings for Robust Hallucination Detection {\&} Grounding in {VLM}s",
    author = "Phukan, Anirudh  and
      Divyansh, Divyansh  and
      Morj, Harshit Kumar  and
      Vaishnavi, Vaishnavi  and
      Saxena, Apoorv  and
      Goswami, Koustava",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/Author-page-Marten-During-lu/2025.naacl-long.488/",
    pages = "9661--9675",
    ISBN = "979-8-89176-189-6",
    abstract = "The rapid development of Large Multimodal Models (LMMs) has significantly advanced multimodal understanding by harnessing the language abilities of Large Language Models (LLMs) and integrating modality-specific encoders. However, LMMs are plagued by hallucinations that limit their reliability and adoption. While traditional methods to detect and mitigate these hallucinations often involve costly training or rely heavily on external models, recent approaches utilizing internal model features present a promising alternative. In this paper, we critically assess the limitations of the state-of-the-art training-free technique, the logit lens, in handling generalized visual hallucinations. We introduce *ContextualLens*, a refined method that leverages contextual token embeddings from middle layers of LMMs. This approach significantly improves hallucination detection and grounding across diverse categories, including actions and OCR, while also excelling in tasks requiring contextual understanding, such as spatial relations and attribute comparison. Our novel grounding technique yields highly precise bounding boxes, facilitating a transition from Zero-Shot Object Segmentation to Grounded Visual Question Answering. Our contributions pave the way for more reliable and interpretable multimodal models."
}