← All threads

VLM Hallucination Circuits

Investigating shared early-layer circuits in vision-language models that drive object hallucinations, and developing diagnostic and mitigation methods.

7 papers

Where this stands

The written synthesis of this thread is for subscribers. Subscribe.

How this thread developed

  1. Oct 2026 · KAIST, NAVER Cloud

    Steering hidden states stabilizes vision-language reasoning against subtle visual changes

    Adds a diagnostic for answer flips under subtle visual changes and a training-free hidden-state steering mitigation, extending VLM hallucination circuit diagnostics.

  2. Oct 2026 · Adobe, Arizona State University

    VQ-tokenized VLMs share a circuit that causes object hallucinations

    Identifies a shared early-layer attention routing circuit that causes object hallucinations and proposes a diagnostic three-gate test and a mitigation through projector swapping.

  3. Oct 2026 · Singapore Institute of Technology, Singapore Management University

    New benchmark tests vision-language models under real-world visibility limits

    Adds a benchmark for evaluating object-level recognition failures under degraded visibility, connecting to hallucination and detection circuits.

  4. Oct 2026 · Sapienza University of Rome, Harvard University

    New dataset isolates and mitigates modality distraction in vision-language models

    MoGround dataset isolates modality distraction, providing a diagnostic tool for VLM hallucination circuits.

  5. 2 further papers

    Oct 2026 · City University of Hong Kong, Apple

    Masking irrelevant image regions exposes hidden uncertainty in multimodal models

    proposes a masking-based uncertainty measure for detecting hallucinations in multimodal models by comparing predictions from original and focused image regions.

5 of 7 papers shown