SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2509.17784 · NeurIPS · 2025

Revealing Multimodal Causality with Large Language Models

Feng Liu, Qi Zhang, Tongliang Liu, Jin Li, Shoujin Wang, Fang Chen, Longbing Cao, Shui Yu

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 2 functions out of this paper's own repositories and ran 0 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
JinLi-i/MLLM-CD canonical 0 of 2
FunctionStatusWhere it lives
extract_counterfactual_data Not yet run JinLi-i/MLLM-CD/counterfactual_utils.py
pointer only (licence: NONE) · get_code("860a1b1ba00cf443")
parse_counterfactual_scenarios Not yet run JinLi-i/MLLM-CD/counterfactual_utils.py
pointer only (licence: NONE) · get_code("fd04bba33d1c46ff")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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. The implementation code and data are available at https: //github.com/JinLi-i/MLLM-CD.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2509.17784")
get_code_for_paper("2509.17784")
have("2509.17784")

Connect an agent — have() is free.