AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Hallucinatory Image Tokens: A Training-free EAZY Approach to Detecting and Mitigating Object Hallucinations in LVLMs

Liwei Che, Tony Qingze Liu, Jing Jia, Weiyi Qin, Ruixiang Tang, Vladimir Pavlovic

ICCV 2025 · Vision-language and multimodal › Multimodal LLMs · approach: Decoding-time hallucination mitigation · 14 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use iterative per-object hallucination detection (ablation)EAZY (LLaVA-1.5) · CHAIRCHAIR_S: 38.8 -> 37.8Improved
use iterative per-object detection (ablation)EAZY (Shikra) · CHAIRCHAIR_S: 26.6 -> 26.2Improved
use iterative per-object detection (ablation)EAZY (LLaVA-NEXT) · CHAIRCHAIR_I: 8.3 -> 8.5Hurt
use layer 15 attention instead of layer 10 (ablation)EAZY (LLaVA-1.5) · CHAIRCHAIR_S: 39.8 -> 38.8Improved
use layer 15 attention instead of layer 25 (ablation)EAZY (LLaVA-1.5) · CHAIRCHAIR_S: 41.7 -> 38.8Improved
zero out at input token space rather than ViT output (ablation)EAZY (LLaVA-1.5) · CHAIRCHAIR_S: 40.4 -> 38.8Improved
zero out at image patches rather than input tokens (ablation)EAZY (LLaVA-1.5) · CHAIRCHAIR_S: 38.8 -> 39.0No clear effect
zero-out replacement instead of average embedding (ablation)top-K HIT processing · Hall-COCOimages without OH: 55.17% -> 68.27%Improved
zero-out replacement instead of random token (ablation)top-K HIT processing · Hall-COCOremoved OH: 63.33% -> 74.17%Improved
zero-out replacement instead of neighbor token (ablation)top-K HIT processing · Hall-COCOremoved OH: 61.25% -> 74.17%Improved
zero out top-5 candidate HITsLLaVA-1.5 · Hall-COCOimages with hallucination: 100% -> 31.73%Improved
use EAZY over best baseline IC for detectionLLaVA-1.5 · Hall-COCOaccuracy: 62.56 -> 78.77Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy