mlsanityData to 14 Oct 2026

Revealing Multimodal Causality with Large Language Models

arXiv 2509.17784 ↗First posted 22 Sep 2025cs.LG cs.AIcited by 3

Not on the map. Why?

Abstract (arXiv)

Uncovering cause-and-effect mechanisms from data is fundamental to scientific progress. While large language models (LLMs) show promise for enhancing causal discovery (CD) from unstructured data, their application to the increasingly prevalent multimodal setting remains a critical challenge. Even with the advent of multimodal LLMs (MLLMs), their efficacy in multimodal CD is hindered by two primary limitations: (1) difficulty in exploring intra- and inter-modal interactions for comprehensive causal variable identification; and (2) insufficiency to handle structural ambiguities with purely observational data. To address these challenges, we propose MLLM-CD, a novel framework for multimodal causal discovery from unstructured data. It consists of three key components: (1) a novel contrastive factor discovery module to identify genuine multimodal factors based on the interactions explored from contrastive sample pairs; (2) a statistical causal structure discovery module to infer causal relationships among discovered factors; and (3) an iterative multimodal counterfactual reasoning module to refine the discovery outcomes iteratively by incorporating the world knowledge and reasoning capabilities of MLLMs. Extensive experiments on both synthetic and real-world datasets demonstrate the effectiveness of the proposed MLLM-CD in revealing genuine factors and causal relationships among them from multimodal unstructured data.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 61 of its 111 references that are in the map. First posted on arXiv 22 Sep 2025.

Builds on

61 of 111 references.

References · 61

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2024A Survey on LLM-as-a-Judgecited by 1,423
  4. 2018DAGs with NO TEARS: Continuous Optimization for Structure Learningcited by 752
  5. 2022Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentationcited by 719
  6. 2023NExT-GPT: Any-to-Any Multimodal LLMcited by 615
  7. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Modelscited by 452
  8. 2024Hallucination of Multimodal Large Language Models: A Surveycited by 388
  9. 2023Causal Reasoning and Large Language Models: Opening a New Frontier for Causalitycited by 353
  10. 2023Generating Images with Multimodal Language Modelscited by 260
  11. 2021D'ya like DAGs? A Survey on Structure Learning and Causal Discoverycited by 211
  12. 2023OpenAGI: When LLM Meets Domain Expertscited by 197
38 more
  1. 2021Simple but Effective: CLIP Embeddings for Embodied AIcited by 191
  2. 2024U-KAN Makes Strong Backbone for Medical Image Segmentation and Generationcited by 179
  3. 2023Knowledge Graph Prompting for Multi-Document Question Answeringcited by 152
  4. 2022Interventional Causal Representation Learningcited by 142
  5. 2024Make Your LLM Fully Utilize the Contextcited by 119
  6. 2023Causal-learn: Causal Discovery in Pythoncited by 109
  7. 2018Robustly Disentangled Causal Mechanisms: Validating Deep Representations for Interventional Robustnesscited by 108
  8. 2017Learning Independent Causal Mechanismscited by 105
  9. 2023Kosmos-G: Generating Images in Context with Multimodal Large Language Modelscited by 105
  10. 2024HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detectioncited by 99
  11. 2024Large Language Model (LLM) for Telecommunications: A Comprehensive Survey on Principles, Key Techniques, and Opportunitiescited by 83
  12. 2021Efficient Neural Causal Discovery without Acyclicity Constraintscited by 82
  13. 2016Discovering Causal Signals in Imagescited by 79
  14. 2020Causal Discovery in Physical Systems from Videoscited by 77
  15. 2018Characterizing and Learning Equivalence Classes of Causal DAGs under Interventionscited by 76
  16. 2019Permutation-Based Causal Structure Learning with Unknown Intervention Targetscited by 69
  17. 2023Causal Discovery with Language Models as Imperfect Expertscited by 64
  18. 2023A Survey on Causal Discovery: Theory and Practicecited by 63
  19. 2024Efficient Causal Graph Discovery Using Large Language Modelscited by 53
  20. 2024Vision-and-Language Navigation via Causal Learningcited by 51
  21. 2024VideoTetris: Towards Compositional Text-to-Video Generationcited by 51
  22. 2023Causal Order: The Key to Leveraging Imperfect Experts in Causal Inferencecited by 48
  23. 2019Neuropathic Pain Diagnosis Simulator for Causal Discovery Algorithm Evaluationcited by 32
  24. 2024Integrating Large Language Models in Causal Discovery: A Statistical Causal Approachcited by 32
  25. 2022Can Foundation Models Talk Causality?cited by 30
  26. 2024ALCM: Autonomous LLM-Augmented Causal Discovery Frameworkcited by 29
  27. 2024Score-based Causal Representation Learning: Linear and General Transformationscited by 27
  28. 2024Multi-Agent Causal Discovery Using Large Language Modelscited by 26
  29. 2024Large Language Models are Effective Priors for Causal Graph Discoverycited by 24
  30. 2022Negative Sampling for Contrastive Representation Learning: A Reviewcited by 23
  31. 2024Marrying Causal Representation Learning with Dynamical Systems for Sciencecited by 23
  32. 2022MissDAG: Causal Discovery in the Presence of Missing Data with Continuous Additive Noise Modelscited by 22
  33. 2023Temporally Disentangled Representation Learning under Unknown Nonstationaritycited by 22
  34. 2023Extending Multi-modal Contrastive Representationscited by 21
  35. 2023Causal Structure Learning Supervised by Large Language Modelcited by 21
  36. 2024CausalBN-Bench: A Comprehensive Benchmark for Causal Learning Capability of LLMscited by 20
  37. 2023Identifying Linearly-Mixed Causal Representations from Multi-Node Interventionscited by 18
  38. 2024Causal Graph Discovery with Retrieval-Augmented Generation based Large Language Modelscited by 16

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026CausalEvolve: Towards Open-Ended Discovery with Causal Scratchpadcited by 3
  2. 2026Towards Robust Endogenous Reasoning: Unifying Drift Adaptation in Non-Stationary Tuningcited by 2
  3. 2026SDVDiag: Using Context-Aware Causality Mining for the Diagnosis of Connected Vehicle Functionscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025Causal MAS: A Survey of Large Language Model Architectures for Discovery and Effect Estimation
  2. 2023Integrating Large Language Model for Improved Causal Discovery
  3. 2024Counterfactual Causal Inference in Natural Language with Large Language Models
  4. 2024OCDB: Revisiting Causal Discovery with a Comprehensive Benchmark and Evaluation Framework
  5. 2025Causal Reasoning in Pieces: Modular In-Context Learning for Causal Discovery
  6. 2024Exploring Multi-Modal Data with Tool-Augmented LLM Agents for Precise Causal Discovery
  7. 2026Leveraging Large Language Models for Causal Discovery: a Constraint-based, Argumentation-driven Approach
  8. 2024Discovering and Reasoning of Causality in the Hidden World with Large Language Models