Seeing Clearly, Answering Incorrectly: A Multimodal Robustness Benchmark for Evaluating MLLMs on Leading Questions

• URL: http://arxiv.org/abs/2406.10638v1
• Date: Sat, 15 Jun 2024 13:58:26 GMT
• Title: Seeing Clearly, Answering Incorrectly: A Multimodal Robustness Benchmark for Evaluating MLLMs on Leading Questions
• Authors: Yexin Liu, Zhengyang Liang, Yueze Wang, Muyang He, Jian Li, Bo Zhao,
• Abstract summary: Most evaluation benchmarks assume that incorrect answers indicate a lack of understanding of the visual content. Our findings reveal that, in many cases, MLLMs answer questions incorrectly despite correctly understanding the visual content. This suggests that incorrect answers do not necessarily imply a lack of comprehension but may instead result from lacking robustness to leading questions.
• Score: 6.41245355860746
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multimodal Large Language Models (MLLMs) have exhibited impressive capabilities in visual understanding and reasoning, providing sightly reasonable answers, such as image descriptions. This has spurred extensive research on the evaluation of MLLMs. Most evaluation benchmarks assume that incorrect answers indicate a lack of understanding of the visual content. However, our findings reveal that, in many cases, MLLMs answer questions incorrectly despite correctly understanding the visual content. This suggests that incorrect answers do not necessarily imply a lack of comprehension but may instead result from lacking robustness to leading questions. To comprehensively measure MLLMs' understanding capability and robustness to leading questions, we introduce a MultiModal Robustness benchmark (MMR). MMR contains paired positive and negative questions across 12 categories, meticulously annotated by humans. We evaluate 18 leading MLLMs on the MMB benchmark, revealing that MLLMs suffer from fragility to leading questions despite understanding the visual content. To enhance MLLMs' understanding capability and robustness, we further present a training set with paired positive and negative visual question-answer samples. Experiments verify that MLLMs' robustness can be significantly enhanced by tuning on this new training set. The benchmark, training set, and code can be found at https://github.com/BAAI-DCAI/Multimodal-Robustness-Benchmark.

Related papers

• Revisiting Multi-Modal LLM Evaluation [29.094387692681337]
  We pioneer evaluating recent MLLMs (LLaVA 1.5, LLaVA-NeXT, BLIP2, InstructBLIP, GPT-4V, and GPT-4o) on datasets designed to address weaknesses in earlier ones. Our code is integrated into the widely used LAVIS framework for MLLM evaluation, enabling the rapid assessment of future MLLMs.
  arXiv  Detail & Related papers  (2024-08-09T20:55:46Z)
• LOVA3: Learning to Visual Question Answering, Asking and Assessment [61.51687164769517]
  Question answering, asking, and assessment are three innate human traits crucial for understanding the world and acquiring knowledge. Current Multimodal Large Language Models (MLLMs) primarily focus on question answering, often neglecting the full potential of questioning and assessment skills. We introduce LOVA3, an innovative framework named "Learning tO Visual question Answering, Asking and Assessment"
  arXiv  Detail & Related papers  (2024-05-23T18:21:59Z)
• MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems? [99.0305256706604]
  We introduce MathVerse, an all-around visual math benchmark designed for an equitable and in-depth evaluation of MLLMs. We meticulously collect 2,612 high-quality, multi-subject math problems with diagrams from publicly available sources. This approach allows MathVerse to comprehensively assess whether and how much MLLMs can truly understand the visual diagrams for mathematical reasoning.
  arXiv  Detail & Related papers  (2024-03-21T17:59:50Z)
• Q-Bench+: A Benchmark for Multi-modal Foundation Models on Low-level Vision from Single Images to Pairs [71.07108539262721]
  We design benchmark settings to emulate human language responses related to low-level vision. We extend the low-level perception-related question-answering and description evaluations of MLLMs from single images to image pairs. We demonstrate that several MLLMs have decent low-level visual competencies on single images, but only GPT-4V exhibits higher accuracy on pairwise comparisons than humans.
  arXiv  Detail & Related papers  (2024-02-11T06:44:11Z)
• MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmark [41.68821233828375]
  This paper introduces a novel benchmark, termed MLLM-as-a-Judge, to assess the ability of MLLMs in assisting judges across diverse modalities. Our study reveals that, while MLLMs demonstrate remarkable human-like discernment in Pair Comparison, there is a significant divergence from human preferences in Scoring Evaluation and Batch Ranking.
  arXiv  Detail & Related papers  (2024-02-07T12:28:32Z)
• The Instinctive Bias: Spurious Images lead to Illusion in MLLMs [34.91795817316696]
  We identify a typical class of inputs that baffles MLLMs, which consist of images that are highly relevant but inconsistent with answers. We propose CorrelationQA, the first benchmark that assesses the visual illusion level given spurious images. We conduct a thorough analysis on 9 mainstream MLLMs, illustrating that they universally suffer from this instinctive bias to varying degrees.
  arXiv  Detail & Related papers  (2024-02-06T06:48:46Z)
• InfiMM-Eval: Complex Open-Ended Reasoning Evaluation For Multi-Modal Large Language Models [50.03163753638256]
  Multi-modal Large Language Models (MLLMs) are increasingly prominent in the field of artificial intelligence. Our benchmark comprises three key reasoning categories: deductive, abductive, and analogical reasoning. We evaluate a selection of representative MLLMs using this rigorously developed open-ended multi-step elaborate reasoning benchmark.
  arXiv  Detail & Related papers  (2023-11-20T07:06:31Z)
• Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision [85.6008224440157]
  Multi-modality Large Language Models (MLLMs) have catalyzed a shift in computer vision from specialized models to general-purpose foundation models. We present Q-Bench, a holistic benchmark crafted to evaluate potential abilities of MLLMs on three realms: low-level visual perception, low-level visual description, and overall visual quality assessment.
  arXiv  Detail & Related papers  (2023-09-25T14:43:43Z)
• MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models [73.86954509967416]
  Multimodal Large Language Model (MLLM) relies on the powerful LLM to perform multimodal tasks. This paper presents the first comprehensive MLLM Evaluation benchmark MME. It measures both perception and cognition abilities on a total of 14 subtasks.
  arXiv  Detail & Related papers  (2023-06-23T09:22:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.