AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

TruthLens: Object Hallucination Detection via Self-Evaluating Truthfulness Scores in LVLMs

Yanqi Wu, Runhe Lai, Xinhua Lu, Qichao Chen, Zhiping Zhou, Jia-Xin Zhuang, Weijiang Yu, Ruixuan Wang

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Decoding-time hallucination mitigation · 0 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
fine-tune with MSE truthfulness objective plus KL (ablation)TruthLens · MSCOCOAUROC: 34.80 -> 89.02Improved
add class-level loss reweighting (ablation)TruthLens · MSCOCOAUROC: 89.02 -> 90.57 (LLaVA-1.5-7B); 85.69 -> 91.46 (Qwen2.5-VL-7B)Improved
keep KL divergence constraint (ablation)TruthLens · MSCOCOgeneration qualityImproved
swap special token (<|image_pad|> vs vision_start/end) (ablation)TruthLens · MSCOCOAUROC: 91.20-91.54 on Qwen2.5-VL-7BNo clear effect
supervise first vs last vs averaged sub-token (ablation)TruthLens · MSCOCOAUROCNo clear effect
increase number of sampled rollouts (ablation)TruthLens · MSCOCOAUROCImproved
use TruthLens fine-tuning on LLaVA-1.5-7BLLaVA-1.5-7B · 13 general benchmarks (e.g. POPE)accuracy: POPE 85.76 -> 85.67; MME 1468.56 -> 1474.59No clear effect
replace best baseline with TruthLensLLaVA-OneVision-1.5-8B · MSCOCOAUROC: 76.94 -> 93.04Improved
train on MSCOCO only, test on Object365TruthLens · Object365AUROC: 72.59 -> 82.14 (LLaVA-OV-1.5-8B vs SVAR)Improved
apply TruthLens-guided caption revisionLLaVA-1.5-7B · MSCOCO captionsCHAIR_s: 49.40 -> 43.78Improved
apply TruthLens to weak-reasoning models on CLEVRLLaVA-1.5 · CLEVRAUROC: 59.89 -> 63.34 (7B)Mixed

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