HALP: Detecting Hallucinations in Vision-Language Models without Generating a Single Token
Hallucinations remain a persistent challenge for vision-language models (VLMs), which often describe nonexistent objects or fabricate facts. Existing detection methods typically operate after text generation, making intervention both costly and untimely. We investigate whether hallucination risk can instead be predicted before any token is generated by probing a model's internal representations in a single forward pass. Across a diverse set of vision-language tasks and eight modern VLMs, including Llama-3.2-Vision, Gemma-3, Phi-4-VL, and Qwen2.5-VL, we examine three families of internal representations: (i) visual-only features without multimodal fusion, (ii) vision-token representations ...
| Authors | Sai Akhil Kogilathota, Sripadha Vallabha E G, Luzhe Sun et al. |
|---|---|
| Primary category | cs.CV |
| Published | 5 March 2026 |
| Last updated at source | 5 March 2026 |
Models and datasets referencing this paper
- Zesearch/HALP-BenchDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.