‹ back to 2026-07-24

HalluScope: Fine-grained Hallucination Diagnosis for Multimodal Large Language Models

Research Multimodal & Generative

Ranking

Overall 72

Content 85

Popularity 42

Observed public metrics from 1 member.

Merged summary

TL;DR - HalluScope introduces a unified framework for detecting, classifying, and explaining hallucinations in multimodal large language models. Its fine-grained diagnoses can also help other models correct hallucinated outputs.

HalluScope-30K covers eight hallucination sources and five task categories.
HalluScope-4B and HalluScope-8B use a multi-granular joint reward to optimize detection and classification together.
The models achieve state-of-the-art results on MHALO and a fine-grained hallucination classification benchmark.
Diagnosis-driven feedback improves hallucination correction in Qwen3-VL-8B-Instruct and LLaVA-1.5-7B.

Sources (1)

HalluScope: Fine-grained Hallucination Diagnosis for Multimodal Large Language Models

arXiv cs.CV Weilin Jin, Mingyu Wang, Wenbo Li, Haoyang Huang, Yifan Wu, Ying Li, Gang Huang, Zhonghai Wu 2026-07-23 arXiv:2607.21105

Public signals Semantic Scholar citations 0 · Semantic Scholar influential citations 0

Providers: Hugging Face · N/A OpenAlex · N/A Publisher · N/A Semantic Scholar · Citations 0 · Influential citations 0 X · N/A Fetched 2026-08-20 14:34:28.191401 UTC

HalluScope-30K covers eight hallucination sources and five task categories.
HalluScope-4B and HalluScope-8B use a multi-granular joint reward to optimize detection and classification together.
The models achieve state-of-the-art results on MHALO and a fine-grained hallucination classification benchmark.
Diagnosis-driven feedback improves hallucination correction in Qwen3-VL-8B-Instruct and LLaVA-1.5-7B.

item →