Causes in neuron diagrams, and testing causal reasoning in Large Language Models. A glimpse of the future of philosophy?
On the map: LLM reasoning → Reasoning benchmarks and evaluation
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 20 of its 48 references that are in the map. First posted on arXiv 17 Jun 2025.
Builds on
20 of 48 references.
Closest ancestors · 4
Same direction, newest first
- 2023GPT-4 Can't Reason21 Jul
- 2023Evaluating the Logical Reasoning Ability of ChatGPT and GPT-47 Apr
- 2023A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity8 Feb
- 2022Towards Reasoning in Large Language Models: A Survey20 Dec
Other references · 16
- 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
- 2017Deep reinforcement learning from human preferencescited by 3,912
- 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
- 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,998
- 2023Causal Reasoning and Large Language Models: Opening a New Frontier for Causalitycited by 353
- 2023Mathematical Capabilities of ChatGPTcited by 268
- 2023Causal Parrots: Large Language Models May Talk Causality But Are Not Causalcited by 150
- 2023Can Large Language Models Infer Causation from Correlation?cited by 146
- 2023Is ChatGPT a Good Causal Reasoner? A Comprehensive Evaluationcited by 69
- 2025PhysReason: A Comprehensive Benchmark towards Physics-Based Reasoningcited by 59
- 2023Causal-Discovery Performance of ChatGPT in the context of Neuropathic Pain Diagnosiscited by 36
- 2023When do you need Chain-of-Thought Prompting for ChatGPT?cited by 35
4 more
- 2023Does ChatGPT have Theory of Mind?cited by 16
- 2023Advances in apparent conceptual physics reasoning in GPT-4cited by 12
- 2023AI Insights into Theoretical Physics and the Swampland Program: A Journey Through the Cosmos with ChatGPTcited by 10
- 2023Towards a Benchmark for Scientific Understanding in Humans and Machinescited by 9
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Recognizing Artificial Minds: A Philosophical Defense of AI Cognition
- 2024Causal Interventions on Causal Paths: Mapping GPT-2's Reasoning From Syntax to Semantics
- 2025Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?
- 2026Generative Interpretability via Scalable Neuro-Symbolic Models
- 2025Nature's Insight: A Novel Framework and Comprehensive Analysis of Agentic Reasoning Through the Lens of Neuroscience
- 2025PEIRCE: Unifying Material and Formal Reasoning via LLM-Driven Neuro-Symbolic Refinement
- 2024A Philosophical Introduction to Language Models -- Part I: Continuity With Classic Debates
- 2025Mitigating Hallucinations in Large Language Models via Causal Reasoning