mlsanityData to 7 Oct 2026

Unveiling the Tapestry of Consistency in Large Vision-Language Models

arXiv 2405.14156 ↗First posted 23 May 2024cs.CVcited by 22

On the map: LLM reasoning → Multimodal reasoning

also in 1 more
Abstract (arXiv)

Large vision-language models (LVLMs) have recently achieved rapid progress, exhibiting great perception and reasoning abilities concerning visual information. However, when faced with prompts in different sizes of solution spaces, LVLMs fail to always give consistent answers regarding the same knowledge point. This inconsistency of answers between different solution spaces is prevalent in LVLMs and erodes trust. To this end, we provide a multi-modal benchmark ConBench, to intuitively analyze how LVLMs perform when the solution space of a prompt revolves around a knowledge point. Based on the ConBench tool, we are the first to reveal the tapestry and get the following findings: (1) In the discriminate realm, the larger the solution space of the prompt, the lower the accuracy of the answers. (2) Establish the relationship between the discriminative and generative realms: the accuracy of the discriminative question type exhibits a strong positive correlation with its Consistency with the caption. (3) Compared to open-source models, closed-source models exhibit a pronounced bias advantage in terms of Consistency. Eventually, we ameliorate the consistency of LVLMs by trigger-based diagnostic refinement, indirectly improving the performance of their caption. We hope this paper will accelerate the research community in better evaluating their models and encourage future advancements in the consistency domain. The project is available at https://github.com/foundation-multimodal-models/ConBench.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. Builds on 23 of its 30 references that are in the map. First posted on arXiv 23 May 2024.

Builds on

23 of 30 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023MMBench: Is Your Multi-modal Model an All-around Player?12 Jul

Other references · 22

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  5. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,069
  6. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  7. 2023Qwen Technical Reportcited by 3,273
  8. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,534
  9. 2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIcited by 2,044
  10. 2023MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Modelscited by 1,624
  11. 2020DocVQA: A Dataset for VQA on Document Imagescited by 1,288
  12. 2023mPLUG-Owl: Modularization Empowers Large Language Models with Multimodalitycited by 1,038
10 more
  1. 2024How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suitescited by 1,033
  2. 2023ShareGPT4V: Improving Large Multi-Modal Models with Better Captionscited by 1,000
  3. 2023SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehensioncited by 929
  4. 2024Are We on the Right Way for Evaluating Large Vision-Language Models?cited by 893
  5. 2023LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attentioncited by 776
  6. 2023CogVLM: Visual Expert for Pretrained Language Modelscited by 704
  7. 2024DeepSeek LLM: Scaling Open-Source Language Models with Longtermismcited by 621
  8. 2024Mini-Gemini: Mining the Potential of Multi-modality Vision Language Modelscited by 361
  9. 2023Generating with Confidence: Uncertainty Quantification for Black-box Large Language Modelscited by 286
  10. 2023Benchmarking and Improving Generator-Validator Consistency of Language Modelscited by 43

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 6; 2025: 11; 2026: 5.

22 papers.

Sort:

By area:

  1. 2024SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inferencecited by 378
  2. 2025RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concretecited by 134
  3. 2025Uncertainty Quantification and Confidence Calibration in Large Language Models: A Surveycited by 93
  4. 2025Traceable Evidence Enhanced Visual Grounded Reasoning: Evaluation and Methodologycited by 67
  5. 2025WoW: Towards a World omniscient World model Through Embodied Interactioncited by 66
  6. 2024Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Surveycited by 52
  7. 2024Unveiling the Ignorance of MLLMs: Seeing Clearly, Answering Incorrectlycited by 29
  8. 2025Robobench: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models as Embodied Braincited by 24
  9. 2024Exploring Response Uncertainty in MLLMs: An Empirical Evaluation under Misleading Scenarioscited by 19
  10. 2024On the Consistency of Video Large Language Models in Temporal Comprehensioncited by 18
  11. 2025When Semantics Mislead Vision: Mitigating Large Multimodal Models Hallucinations in Scene Text Spotting and Understandingcited by 12
  12. 2026Wow, wo, val! A Comprehensive Embodied World Model Evaluation Turing Testcited by 11
10 more
  1. 2025ZoomV: Temporal Zoom-in for Efficient Long Video Understandingcited by 10
  2. 2025When Continue Learning Meets Multimodal Large Language Model: A Surveycited by 8
  3. 2025MedMMV: A Controllable Multimodal Multi-Agent Framework for Reliable and Verifiable Clinical Reasoningcited by 8
  4. 2026Instinct vs. Reflection: Unifying Token and Verbalized Confidence in Multimodal Large Modelscited by 3
  5. 2024Evaluating and Advancing Multimodal Large Language Models in Perception Ability Lenscited by 2
  6. 2025AutoV: Loss-Oriented Ranking for Visual Prompt Retrieval in LVLMscited by 2
  7. 2025Value-Guided Iterative Refinement and the DIQ-H Benchmark for Evaluating VLM Robustnesscited by 1
  8. 2026SEED: Targeted Data Selection by Weighted Independent Setcited by 1
  9. 2026Towards Annotation-Free Validation of MLLMs: A Vision-Language Logical Consistency Metriccited by 0
  10. 2026VISTA: Auditing Semantic Divergence in Vision-Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024MM-R3: On (In-)Consistency of Vision-Language Models (VLMs)
  2. 2026Do Vision-Language Models See or Guess? Measuring and Reducing Textual-Prior Reliance with a Phrasing-Controlled Benchmark
  3. 2025Test-Time Consistency in Vision Language Models
  4. 2026Seeing Isn't Believing: Uncovering Blind Spots in Evaluator Vision-Language Models
  5. 2024Unraveling Cross-Modality Knowledge Conflicts in Large Vision-Language Models
  6. 2024FiVL: A Framework for Improved Vision-Language Alignment through the Lens of Training, Evaluation and Explainability
  7. 2025Where do Large Vision-Language Models Look at when Answering Questions?
  8. 2026Seeing and Solving Are Not Enough for Vision-Language Models