Hallucination of multimodal large language models: A survey

Z Bai, P Wang, T **ao, T He, Z Han, Z Zhang… - arxiv preprint arxiv …, 2024‏ - arxiv.org
This survey presents a comprehensive analysis of the phenomenon of hallucination in
multimodal large language models (MLLMs), also known as Large Vision-Language Models …

Evaluating and analyzing relationship hallucinations in large vision-language models

M Wu, J Ji, O Huang, J Li, Y Wu, X Sun, R Ji - arxiv preprint arxiv …, 2024‏ - arxiv.org
The issue of hallucinations is a prevalent concern in existing Large Vision-Language
Models (LVLMs). Previous efforts have primarily focused on investigating object …

MMRel: A Relation Understanding Dataset and Benchmark in the MLLM Era

J Nie, G Zhang, W An, YP Tan, AC Kot, S Lu - arxiv preprint arxiv …, 2024‏ - arxiv.org
Despite the recent advancements in Multi-modal Large Language Models (MLLMs),
understanding inter-object relations, ie, interactions or associations between distinct objects …

Pensieve: Retrospect-then-compare mitigates visual hallucination

D Yang, B Cao, G Chen, C Jiang - arxiv preprint arxiv:2403.14401, 2024‏ - arxiv.org
Multi-modal Large Language Models (MLLMs) demonstrate remarkable success across
various vision-language tasks. However, they suffer from visual hallucination, where the …

VALOR-EVAL: Holistic Coverage and Faithfulness Evaluation of Large Vision-Language Models

H Qiu, W Hu, ZY Dou, N Peng - arxiv preprint arxiv:2404.13874, 2024‏ - arxiv.org
Large Vision-Language Models (LVLMs) suffer from hallucination issues, wherein the
models generate plausible-sounding but factually incorrect outputs, undermining their …

LightHouse: A Survey of AGI Hallucination

F Wang - arxiv preprint arxiv:2401.06792, 2024‏ - arxiv.org
With the development of artificial intelligence, large-scale models have become increasingly
intelligent. However, numerous studies indicate that hallucinations within these large …

A Survey of Hallucination in Large Visual Language Models

W Lan, W Chen, Q Chen, S Pan, H Zhou… - arxiv preprint arxiv …, 2024‏ - arxiv.org
The Large Visual Language Models (LVLMs) enhances user interaction and enriches user
experience by integrating visual modality on the basis of the Large Language Models …

Advancing Large Vision-Language Models with Efficiency, Reliability and Visual Knowledge

W Hu - 2024‏ - search.proquest.com
UNIVERSITY OF CALIFORNIA Los Angeles Advancing Large Vision-Language Models with
Efficiency, Reliability and Visual Knowledge A Page 1 UNIVERSITY OF CALIFORNIA Los …