VisDiaHalBench: A Visual Dialogue Benchmark For Diagnosing Hallucination in Large Vision-Language Models

Qingxing Cao, Junhao Cheng, Xiaodan Liang, Liang Lin


Abstract
Despite the significant success of large vision-language models (LVLMs), some studies have revealed that LVLMs suffer from the hallucination problem, where the LVLMs’ response contains descriptions of non-existent objects. Although various benchmarks have been proposed to investigate this problem, they mostly focus on single-turn evaluation and overlook the hallucination raised by textual inputs. To investigate the hallucination problem of LVLMs when given long-term misleading textual history, we propose a novel visual dialogue hallucination evaluation benchmark VisDiaHalBench. The benchmark consists of samples with five-turn questions about an edited image and its original version. VisDiaHalBench differs from previous hallucination benchmarks in the following three points: 1) The questions and answers are unambiguously grounded by annotated scene graphs. 2) The images are uncommonly edited to inspect the visual model and common-object hallucination in LLMs. 3) The carefully designed dialogue refers a same object in different turns to assess the image consistency and influence of history for LVLMs. The detailed analysis of several state-of-the-art LVLMs across image consistency, visual understanding, history influence, and other dimensions reveals their substantial performance gap with single-turn VQA tasks. The benchmark is released in: https://github.com/qingxingcao/VisDiaHalBench
Anthology ID:
2024.acl-long.658
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
12161–12176
Language:
URL:
https://aclanthology.org/2024.acl-long.658
DOI:
10.18653/v1/2024.acl-long.658
Bibkey:
Cite (ACL):
Qingxing Cao, Junhao Cheng, Xiaodan Liang, and Liang Lin. 2024. VisDiaHalBench: A Visual Dialogue Benchmark For Diagnosing Hallucination in Large Vision-Language Models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 12161–12176, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
VisDiaHalBench: A Visual Dialogue Benchmark For Diagnosing Hallucination in Large Vision-Language Models (Cao et al., ACL 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/2024.acl-long.658.pdf