# Do Vision & Language Decoders use Images and Text equally? How Self-consistent are their Explanations?

arXiv: https://arxiv.org/abs/2404.18624 · HTML: https://mlsanity.com/paper/2404.18624/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 44 of its 59 references that are in the map.
- First posted on arXiv 29 Apr 2024.

## Builds on (most cited first, 30 of 44)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [On the Properties of Neural Machine Translation: Encoder-Decoder Approaches](https://mlsanity.com/paper/1409.1259/) (2014)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [Vision-Language Models for Vision Tasks: A Survey](https://mlsanity.com/paper/2304.00685/) (2023)
- [Measuring Faithfulness in Chain-of-Thought Reasoning](https://mlsanity.com/paper/2307.13702/) (2023)
- [Multimodal Few-Shot Learning with Frozen Language Models](https://mlsanity.com/paper/2106.13884/) (2021)
- [When and why vision-language models behave like bags-of-words, and what to do about it?](https://mlsanity.com/paper/2210.01936/) (2022)
- [Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?](https://mlsanity.com/paper/2004.03685/) (2020)
- [OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models](https://mlsanity.com/paper/2308.01390/) (2023)
- [Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality](https://mlsanity.com/paper/2204.03162/) (2022)
- [Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond](https://mlsanity.com/paper/2304.13712/) (2023)
- [SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression](https://mlsanity.com/paper/2306.03078/) (2023)
- [MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training](https://mlsanity.com/paper/2403.09611/) (2024)
- [CREPE: Can Vision-Language Foundation Models Reason Compositionally?](https://mlsanity.com/paper/2212.07796/) (2022)
- [Measuring Association Between Labels and Free-Text Rationales](https://mlsanity.com/paper/2010.12762/) (2020)
- [VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena](https://mlsanity.com/paper/2112.07566/) (2021)

## Built on by (most cited first, 24 of 24)

- [Evaluating and Steering Modality Preferences in Multimodal Large Language Model](https://mlsanity.com/paper/2505.20977/) (2025)
- [When Modalities Conflict: How Unimodal Reasoning Uncertainty Governs Preference Dynamics in MLLMs](https://mlsanity.com/paper/2511.02243/) (2025)
- [Cracking the Code of Hallucination in LVLMs with Vision-aware Head Divergence](https://mlsanity.com/paper/2412.13949/) (2024)
- [Performance Gap in Entity Knowledge Extraction Across Modalities in Vision Language Models](https://mlsanity.com/paper/2412.14133/) (2024)
- [Advancing Reliable Test-Time Adaptation of Vision-Language Models under Visual Variations](https://mlsanity.com/paper/2507.09500/) (2025)
- [Explaining Similarity in Vision-Language Encoders with Weighted Banzhaf Interactions](https://mlsanity.com/paper/2508.05430/) (2025)
- [Beyond Cross-Modal Alignment: Measuring and Leveraging Modality Gap in Vision-Language Models](https://mlsanity.com/paper/2502.14888/) (2025)
- [VISaGE: Understanding Visual Generics and Exceptions](https://mlsanity.com/paper/2510.12548/) (2025)
- [Can VLMs Recall Factual Associations From Visual References?](https://mlsanity.com/paper/2508.18297/) (2025)
- [Grounding or Guessing? Visual Signals for Detecting Hallucinations in Sign Language Translation](https://mlsanity.com/paper/2510.18439/) (2025)
- [On the Risk of Misleading Reports: Diagnosing Textual Biases in Multimodal Clinical AI](https://mlsanity.com/paper/2508.00171/) (2025)
- [Investigating Modality Contribution in Audio LLMs for Music](https://mlsanity.com/paper/2509.20641/) (2025)
- [CAST: Cross-modal Alignment Similarity Test for Vision Language Models](https://mlsanity.com/paper/2409.11007/) (2024)
- [When to Call an Apple Red: Humans Follow Introspective Rules, VLMs Don't](https://mlsanity.com/paper/2604.06422/) (2026)
- [Medical Context Distorts Decisions in Clinical Vision Language Models](https://mlsanity.com/paper/2605.17436/) (2026)
- [VisualLens: Personalization through Task-Agnostic Visual History](https://mlsanity.com/paper/2411.16034/) (2024)
- [A Video Is Not Worth a Thousand Words](https://mlsanity.com/paper/2510.23253/) (2025)
- [System-Mediated Attention Imbalances Make Vision-Language Models Say Yes](https://mlsanity.com/paper/2601.12430/) (2026)
- [TemporalDoRA: Temporal PEFT for Robust Surgical Video Question Answering](https://mlsanity.com/paper/2603.09696/) (2026)
- [Faithful Action-unit Causal Reasoning for Counterfactually Faithful Emotion Explanations](https://mlsanity.com/paper/2606.15779/) (2026)
- [When Seeing Overrides Knowing: Visual Dominance and Deferral-Based Method for Personalized Safety in VLMs](https://mlsanity.com/paper/2609.04281/) (2026)
- [I Don't Miss You, but I Do: Self-Explanation Faithfulness of Modality Missingness in Vision-Language Models](https://mlsanity.com/paper/2609.07596/) (2026)
- [AnswerMap: Faithful Spatial Interpretability of VLMs from Answer Posteriors](https://mlsanity.com/paper/2609.35247/) (2026)
- [Cross-Modal Latent Influence: Patch-Level Training Sample Attribution for Vision-Language Models](https://mlsanity.com/paper/2610.14190/) (2026)

## Abstract (arXiv)

Vision and language model (VLM) decoders are currently the best-performing architectures on multimodal tasks. Next to answers, they are able to produce natural language explanations, either in post-hoc or CoT settings. However, it is not clear to what extent they are using the input vision and text modalities when generating answers or explanations. In this work, we investigate if VLMs rely on their input modalities differently when they produce explanations as opposed to answers. We also evaluate the self-consistency of VLM decoders in both post-hoc and CoT explanation settings, by extending existing unimodal tests and measures to VLM decoders. We find that most tested VLMs are less self-consistent than LLMs. Text contributions in all tested VL decoders are more important than image contributions in all examined tasks. However, when comparing explanation generation to answer generation, the contributions of images are significantly stronger for generating explanations compared to answers. This difference is even larger in CoT compared to post-hoc explanations. Lastly, we provide an up-to-date benchmarking of state-of-the-art VL decoders on the VALSE benchmark, which before was restricted to VL encoders. We find that the tested VL decoders still struggle with most phenomena tested by VALSE.