Causal Reasoning in Language Models

Follow this topic Ask about this topic

The field asks whether language models can go beyond patterns of correlation to identify causes, predict what would happen under interventions, and reason about what might have happened otherwise. Researchers test these abilities with causal graphs, counterfactual questions, context-sensitive tasks in areas such as medicine and policy, and interactive settings where models must choose experiments. Approaches include prompting with explicit graphs, retrieval and tool use, multi-agent experiment design, and training with simulated interventions or step-level feedback. Models can handle some familiar causal patterns, but often confuse association with cause, miss context changes, or give fluent answers unsupported by a valid causal path; a central challenge is distinguishing genuine causal competence from shortcuts in language or benchmark performance.

Latest papers

102 papers13 papers in the last four weeks, up 30% on the four weeks before. 0.1% of all new papers.

From Document Layout to Causal Topology: An End-to-End Architecture for Temporal Causal Reasoning
Oct 25, 2026Zhifeng Yang, Wei Luo, Yongjian Chen +1Causal Reasoning in Language Models Temporal Reasoning in Language Models
School of Future Technology, South China University of Technology · Guangdong Artificial Intelligence and Digital Economy Laboratory (Guangzhou)
CauProphet: Teaching Agents to Develop Causal Cognition like Humans
Oct 23, 2026Kaiwen Wu, Chaochao LuCausal Reasoning in Language Models Continual Learning for LLM Agents
Shanghai Jiao Tong University · Shanghai AI Laboratory
Causal Chain of Thought: Mitigating Attention Leakage via Context Isolation
Oct 22, 2026Gabriele Dominici, Teague McMillan, Fazl Barez +2Structured Reasoning in Language Models Faithfulness of Language Model Reasoning
Università della Svizzera Italiana · ETH Zurich · University of Oxford
From Observation to Intervention: Distilling Self-Generated In-Context Demonstrations via Executable Causal Intervention
Oct 15, 2026Minming Ye, Min Liu, Haoang Chi +2In-Context Learning In-Context Example Selection
Shanghai Jiaotong University · Academy of Military Science · National University of Defense Technology
ACED-Bench: Evaluating How LLM Agents Acquire and Act on Causal Evidence
Oct 9, 2026Yiwei Chen, Amila Weerasinghe, Siddharth Biswal +4AI Agent Benchmarks Causal Reasoning in Language Models
UC San Diego · Amazon
Illusory Pattern Perception Drives Spurious Inference in Large Language Models
Oct 6, 2026Peihua Mai, Zhuoyan Shao, Xinbao Qiao +3Causal Reasoning in Language Models
National University of Singapore (Chongqing) Research Institute · Chongqing Key Laboratory of Trusted Perception and Interaction Technology for Intelligent and Connected Vehicles, Chongqing, China · National University of Singapore +3
Readable Before Actionable: Causal Tracing of Indirect Prompt Injection
Oct 4, 2026Zhe Yu, Wenpeng Xing, Xingxing Yang +1Causal Reasoning in Language Models Indirect Prompt Injection
Zhejiang University · Binjiang Institute of Zhejiang University · Hong Kong Baptist University
Reasoning Models Are Accurate but Unsound on Identification
Oct 2, 2026Arman Behnam, Binghui WangQuery Identifiability Causal Identifiability
Department of Computer Science Illinois Institute of Technology Chicago, IL, USA
To Explore The Strange New World Beyond Data Distribution: System Behavior, Causality Tax, and Non-causal Base Model
Oct 2, 2026Xianzhi Zeng, Jiangneng Li, Gao CongCausal Reasoning in Language Models Variational Inference
College of Computing and Data Science Nanyang Technological University Singapore, 639798
THPL: A Vision-to-Language Decision Support Framework for Rainbow Trout Feeding Management in RAS
Oct 1, 2026Meng Liang, Guanbo Feng, Haozhuang Chi +7LLM Decision-Making Causal Reasoning in Language Models
College of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310058, Zhejiang, PR China · School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore 639798, Singapore · College of Marine Technology and Environment, Dalian Ocean University, Dalian 116023, Liaoning, PR China +1
Inferring Causal Relations between Two Sequences of Events with Language Models
Sep 30, 2026Nishchal Prasad, Eric Gaussier, Emilie Devijver +3Time-Series Causal Discovery Causal Discovery
INRIA, Univ. Grenoble Alpes, CNRS, LIG · Univ. Grenoble Alpes, CNRS, Grenoble INP, LIG · Univ. Grenoble Alpes, CNRS, Inria, Grenoble INP, LIG +1
CHAIN: Calibrated LLM Forecasting via Causal-Temporal Hypergraph Inference
Sep 29, 2026Wenjin Liu, Chenxi Wang, Yue Lu +2Probabilistic Forecasting Language Model Calibration
Hithink research · Nanyang Technological University
Small transformers track Bayesian evidence for latent common causes via a context-invariant mechanism
Sep 28, 2026Amir Mohammadpour, Michael FrankeBayesian Inference Causal Reasoning in Language Models
Department of Linguistics, University of Tübingen
World Agent: Can Language Models Keep a World Running?
Sep 26, 2026Weixing Chen, Weipeng Zhang, Nan An +2World Model Evaluation World Models
Sun Yat-sen University · South China University of Technology · Guangdong Key Laboratory of Big Data Analysis and Processing +2
Externalized CPDAG Summaries Improve LLM Causal Deduction
Sep 25, 2026Wentao Sun, João Paulo Nogueira, Dominique Verchere +2Causal Reasoning in Language Models Causal Reasoning
Nokia Bell Labs · Télécom SudParis · IRISA
Contextual Causality with Large Language Models: A Survey
Sep 18, 2026Yiheng Zhao, Jun Yan, Chengming HuCausal Reasoning in Language Models Causal Interventions in Language Models
Concordia University, Montreal, Canada · Mcgill University, Montreal, Canada
CaLR: Causal Latent Revision for Robust Diffusion Reasoning
Sep 17, 2026Wei Cai, Jian Zhao, Yuchen Yuan +1Reasoning Consistency in Language Models Diffusion Language Models
Peking University
TRACE: Training Reasoning Agents for Causal Exploration with Synthesized Rewards
Sep 9, 2026Rui Sun, Zhan Shi, Bing HeRL for Language Model Reasoning Causal Reasoning in Language Models
Independent Researchers
CausalVerify: End-to-End Verification of Causal Analyses by Language Models
Sep 7, 2026Yonghong Zhang, Ricardo Correia, Isabel M. Parra +1LLM Evaluation Causal Effect Estimation
Department of Finance Universidad Autónoma de Madrid Madrid, Spain · Spanish National Research Council (CSIC) Madrid, Spain
SerenAI: State-transition system inspired by text-based world AI models
Sep 6, 2026Elvin Babayev, Artem Sinitsa, Arash Hajisharifi +1LLM World Models Causal Reasoning in Language Models
Collision Technologies S.R.L.S. Societa Benefit Trieste, Italy
From Deceptive Outputs to Deceptive Mechanisms: A Causal Framework for Language-Model Deception Research
Sep 3, 2026Yakov Pyotr ShkolnikovDeception in Language Models Causal Reasoning in Language Models
Independent Researcher
CRAFT: Fine-Tuning Pre-hoc Explainability in AI-native 6G RAN
Sep 1, 2026Pranshav Gajjar, Vijay K Shah6G Networks LLM Interpretability
NextG Wireless Lab NCSU Raleigh USA
Generative artificial intelligence for reliable mechanistic reasoning for corrosion
Aug 31, 2026M N Bharath, R K Singh Raman, Alankar AlankarRetrieval-Augmented Generation Causal Reasoning in Language Models
Department of Mechanical and Aerospace Engineering, Monash University, Clayton 3800, Victoria, Australia · Center for Machine Intelligence and Data Science, Indian Institute of Technology Bombay, Mumbai, Maharashtra, 400076, India
Medical Causal Hypothesis Verification with Large Language Models
Aug 30, 2026Safiyyah Ahmed, Abrar Ansari, Md Aminul Islam +1Medical LLMs Causal Reasoning in Language Models
University of Illinois Chicago Chicago, IL, USA
SUP-MIMIC: A Multi-Task Clinical Diagnosis Benchmark for Evaluating LLMs' Robustness to Contradictory Evidence
Aug 30, 2026Yi Yu, Bo Wang, Chong Feng +4Clinical Language Model Evaluation Medical LLMs
Beijing University of Technology · Beijing Institute of Technology · Department of Rheumatology and Immunology, China-Japan Friendship Hospital +1
The Illusion of $\textit{What If}$ : Evaluating the Breakdown of Counterfactual Reasoning in LLMs
Aug 28, 2026Yucheng Wang, Yuetian Du, Zhengyi Liu +8Counterfactual Reasoning in Language Models Counterfactual Reasoning
Zhejiang University · Alibaba Group · City University of Hong Kong
SCIT: Testing Causal Cache Carriers in Latent Chain-of-Thought Models
Aug 27, 2026Yi Ding, Lijun Huang, Menglin YangTransformer Interpretability Causal Interventions in Language Models
The Hong Kong University of Science and Technology (Guangzhou) Guangzhou, China
Short Horizons and Sparse Concepts: a Mathematical View of the Readout in the J-lens
Aug 26, 2026Shi-Qi Yan, Kai-Xuan Ding, Chao-Hong Tan +4Transformer Interpretability Implicit Reasoning in Language Models
Alibaba Token Hub, Alibaba Group
From Causal Plausibility to Causal Reliability: Evaluating LLMs as Calibrated Direct Causal-Edge Classifiers
Aug 24, 2026Amit Kumar, Elnur Adl Zarabi, Suranjana Trivedy +4Causal Reasoning in Language Models Causal Structure Learning
Texas A&M University-Corpus Christi, USA · BITS Pilani Goa, India · Mississippi State University, USA +2
CaRGo-T: Causal Reasoning Graph-of-Thought improves Multimodal Humor Comprehension
Aug 24, 2026Abhilash Nandy, Rahul Seetharaman, Aman Bansal +5LLM Reasoning with Graphs Multimodal Reasoning
Indian Institute of Technology Kharagpur, India · Microsoft Research India · LinkedIn, USA +4

Oct 25, 2026J/K move · Enter open · S save

From Document Layout to Causal Topology: An End-to-End Architecture for Temporal Causal Reasoning

Zhifeng Yang, Wei Luo, Yongjian Chen, Shiqi Ou

School of Future Technology, South China University of Technology · Guangdong Artificial Intelligence and Digital Economy Laboratory (Guangzhou)

Causal Reasoning in Language Models Temporal Reasoning in Language Models Causal Reasoning Counterfactual Reasoning in Language Models Neuro-Symbolic Reasoning

Open paper AskPDF arXiv

Large language models (LLMs) generally lack deep causal reasoning capabilities in temporal reasoning. Inspired by document layout reordering, this paper proposes a paradigm shift from discrete narratives to causal topologies. It constructs two architectures: a training-free neuro-symbolic framework, temporal causal reasoning agent (TCR-Agent), which achieves interpretable causal deduction and counterfactual truncation through external causal graph instantiation and a symbolic intervention engine; and an end-to-end model, temporal causal reasoning former (TCR-Former), which internalizes these mechanisms into the Transformer attention space via a Causal-Topological Attention Mask and temporal span biases. Experiments on the TempoCausal benchmark demonstrate that TCR-Agent comprehensively surpasses existing training-free baselines. At the same time, TCR-Former achieves an accuracy 16.5% higher than that of state-of-the-art (SOTA) methods, outperforming large-scale models such as GPT-5.4 and DeepSeek-V3.2 with only approximately 8.6B parameters. Further analysis reveals a structure-reasoning disconnection phenomenon in existing methods: external symbolic constraints and chain-of-thought reasoning can improve reasoning steps, yet fail to enhance deep causal deductive capability. By internalizing temporal causal reasoning capabilities into the model, TCR-Former effectively bridges this gap, providing an efficient and reliable end-to-end foundation for complex reasoning scenarios.