Quantifying and Mitigating Unimodal Biases in Multimodal Large Language Models: A Causal Perspective
- URL: http://arxiv.org/abs/2403.18346v3
- Date: Wed, 3 Apr 2024 17:18:51 GMT
- Title: Quantifying and Mitigating Unimodal Biases in Multimodal Large Language Models: A Causal Perspective
- Authors: Meiqi Chen, Yixin Cao, Yan Zhang, Chaochao Lu,
- Abstract summary: We propose a causal framework to interpret the biases in Visual Question Answering problems.
Motivated by the causal graph, we introduce a novel MORE dataset, consisting of 12,000 VQA instances.
We propose two strategies to enhance MLLMs' reasoning capabilities, including a Decompose-Verify-Answer framework.
- Score: 9.633811630889237
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Recent advancements in Large Language Models (LLMs) have facilitated the development of Multimodal LLMs (MLLMs). Despite their impressive capabilities, MLLMs often suffer from an over-reliance on unimodal biases (e.g., language bias and vision bias), leading to incorrect answers in complex multimodal tasks. To investigate this issue, we propose a causal framework to interpret the biases in Visual Question Answering (VQA) problems. Within our framework, we devise a causal graph to elucidate the predictions of MLLMs on VQA problems, and assess the causal effect of biases through an in-depth causal analysis. Motivated by the causal graph, we introduce a novel MORE dataset, consisting of 12,000 VQA instances. This dataset is designed to challenge MLLMs' abilities, necessitating multi-hop reasoning and the surmounting of unimodal biases. Furthermore, we propose two strategies to mitigate unimodal biases and enhance MLLMs' reasoning capabilities, including a Decompose-Verify-Answer (DeVA) framework for limited-access MLLMs and the refinement of open-source MLLMs through fine-tuning. Extensive quantitative and qualitative experiments offer valuable insights for future research. Our project page is at https://opencausalab.github.io/MORE.
Related papers
- Can Multimodal Large Language Model Think Analogically? [9.517193263050228]
Multimodal Large Language Model (MLLM) has recently sparked considerable discussion due to its emergent capabilities.
We explore two facets: textitMLLM as an explainer and textitMLLM as a predictor
We propose a unified prompt template and a method for harnessing the comprehension capabilities of MLLM to augment existing models.
arXiv Detail & Related papers (2024-11-02T16:59:49Z) - LLaVA-KD: A Framework of Distilling Multimodal Large Language Models [70.19607283302712]
We propose a novel framework to transfer knowledge from l-MLLM to s-MLLM.
Specifically, we introduce Multimodal Distillation (MDist) to minimize the divergence between the visual-textual output distributions of l-MLLM and s-MLLM.
We also propose a three-stage training scheme to fully exploit the potential of s-MLLM.
arXiv Detail & Related papers (2024-10-21T17:41:28Z) - Assessing Modality Bias in Video Question Answering Benchmarks with Multimodal Large Language Models [12.841405829775852]
We introduce the modality importance score (MIS) to identify bias inVidQA benchmarks and datasets.
We also propose an innovative method using state-of-the-art MLLMs to estimate the modality importance.
Our results indicate that current models do not effectively integrate information due to modality imbalance in existing datasets.
arXiv Detail & Related papers (2024-08-22T23:32:42Z) - A Survey on Benchmarks of Multimodal Large Language Models [65.87641718350639]
This paper presents a comprehensive review of 200 benchmarks and evaluations for Multimodal Large Language Models (MLLMs)
We focus on (1)perception and understanding, (2)cognition and reasoning, (3)specific domains, (4)key capabilities, and (5)other modalities.
Our key argument is that evaluation should be regarded as a crucial discipline to support the development of MLLMs better.
arXiv Detail & Related papers (2024-08-16T09:52:02Z) - MM-SpuBench: Towards Better Understanding of Spurious Biases in Multimodal LLMs [38.93090238335506]
Spurious bias, a tendency to use spurious correlations between non-essential input attributes and target variables for predictions, has revealed a severe pitfall in deep learning models trained on single modality data.
We introduce MM-SpuBench, a comprehensive visual question-answering (VQA) benchmark designed to evaluate MLLMs' reliance on nine distinct categories of spurious correlations.
Our findings illuminate the persistence of the reliance on spurious correlations from these models and underscore the urge for new methodologies to mitigate spurious biases.
arXiv Detail & Related papers (2024-06-24T20:29:16Z) - MMRel: A Relation Understanding Dataset and Benchmark in the MLLM Era [72.95901753186227]
Multi-Modal Relation Understanding (MMRel) is a comprehensive dataset for studying inter-object relations with Multi-modal Large Language Models (MLLMs)
MMRel features three distinctive attributes: (i) It includes over 15K question-answer pairs, which are sourced from three distinct domains, ensuring large scale and high diversity; (ii) It contains a subset featuring highly unusual relations, on which MLLMs often fail due to hallucinations, thus are very challenging; (iii) It provides manually verified high-quality labels for inter-object relations.
arXiv Detail & Related papers (2024-06-13T13:51:59Z) - Efficient Multimodal Large Language Models: A Survey [60.7614299984182]
Multimodal Large Language Models (MLLMs) have demonstrated remarkable performance in tasks such as visual question answering, visual understanding and reasoning.
The extensive model size and high training and inference costs have hindered the widespread application of MLLMs in academia and industry.
This survey provides a comprehensive and systematic review of the current state of efficient MLLMs.
arXiv Detail & Related papers (2024-05-17T12:37:10Z) - Eyes Can Deceive: Benchmarking Counterfactual Reasoning Abilities of Multi-modal Large Language Models [31.53954631903559]
We introduce a novel textbfCountertextbfFactual textbfMultitextbfModal reasoning benchmark, abbreviated as textbfCFMM.
Our CFMM comprises six challenging tasks, each including hundreds of carefully human-labeled and GPT-generated counterfactual questions.
We find that existing MLLMs prefer to believe what they see, but ignore the counterfactual presuppositions presented in the question.
arXiv Detail & Related papers (2024-04-19T15:53:27Z) - Multimodal Large Language Models to Support Real-World Fact-Checking [80.41047725487645]
Multimodal large language models (MLLMs) carry the potential to support humans in processing vast amounts of information.
While MLLMs are already being used as a fact-checking tool, their abilities and limitations in this regard are understudied.
We propose a framework for systematically assessing the capacity of current multimodal models to facilitate real-world fact-checking.
arXiv Detail & Related papers (2024-03-06T11:32:41Z) - The Curious Case of Nonverbal Abstract Reasoning with Multi-Modal Large Language Models [19.213774611556]
Multi-modal large language models (MLLMs) integrate verbal and visual information.
Despite the revolutionizing prospect of MLLMs, our understanding of their reasoning abilities is limited.
In this study, we assess the nonverbal abstract reasoning abilities of open-source and closed-source MLLMs.
arXiv Detail & Related papers (2024-01-22T16:57:05Z) - A Survey on Multimodal Large Language Models [71.63375558033364]
Multimodal Large Language Model (MLLM) represented by GPT-4V has been a new rising research hotspot.
This paper aims to trace and summarize the recent progress of MLLMs.
arXiv Detail & Related papers (2023-06-23T15:21:52Z)
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.