Causes in neuron diagrams, and testing causal reasoning in Large Language Models. A glimpse of the future of philosophy?

2025/06/17 by Louis Vervoort, Vitaly Nikolaev, Vervoort, Louis +1
Computer Science · #Artificial Intelligence (cs.AI) #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2506.14239

openalex publication_date 2025/06/17 · openalex created_date 2025/10/18 · openalex updated_date 2026/07/28

Abstract

We propose a test for abstract causal reasoning in AI, based on scholarship in the philosophy of causation, in particular on the neuron diagrams popularized by D. Lewis. We illustrate the test on advanced Large Language Models (ChatGPT, DeepSeek and Gemini). Remarkably, these chatbots are already capable of correctly identifying causes in cases that are hotly debated in the literature. In order to assess the results of these LLMs and future dedicated AI, we propose a definition of cause in neuron diagrams with a wider validity than published hitherto, which challenges the widespread view that such a definition is elusive. We submit that these results are an illustration of how future philosophical research might evolve: as an interplay between human and artificial expertise.

Citations

• PhysReason: A Comprehensive Benchmark towards Physics-Based Reasoning
• DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning
• GPT-4 Can't Reason
• Can Large Language Models Infer Causation from Correlation?
• Does ChatGPT have Theory of Mind?
• Is ChatGPT a Good Causal Reasoner? A Comprehensive Evaluation
• Causal Reasoning and Large Language Models: Opening a New Frontier for Causality
• Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4
• When do you need Chain-of-Thought Prompting for ChatGPT?
• Advances in apparent conceptual physics reasoning in GPT-4
• Sparks of Artificial General Intelligence: Early experiments with GPT-4
• AI as Agency Without Intelligence: on ChatGPT, Large Language Models, and Other Generative Models
• A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity
• Causal-Discovery Performance of ChatGPT in the context of Neuropathic Pain Diagnosis
• AI Insights into Theoretical Physics and the Swampland Program: A Journey Through the Cosmos with ChatGPT
• Towards Reasoning in Large Language Models: A Survey
• Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
• Deep reinforcement learning from human preferences
• Prevention, Preemption, and the Principle of Sufficient Reason
• The Intransitivity of Causation Revealed in Equations and Graphs
• Large Language Models and Causal Inference in Collaboration: A Survey
• Machine Psychology

Related

• "Cause" is Mechanistic Narrative within Scientific Domains: An Ordinary Language Philosophical Critique of "Causal Machine Learning"
• Is Knowledge All Large Language Models Needed for Causal Reasoning?
• Do Large Language Models Reason Causally Like Us? Even Better?
• Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?
• The role of causality in explainable artificial intelligence