Causal Reasoning in Language Models

Follow this topic Ask about this topic

Momentum

5 papers in the last four weeks, up 25% on the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 57

All topics

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
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
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
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: An Execution-Grounded Benchmark for LLM Causal Inference Workflows
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
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, 2026Bharath M N, R K Singh Raman, Alankar AlankarRetrieval-Augmented Generation Causal Reasoning in Language Models
Department of Mechanical Engineering, Indian Institute of Technology Bombay, Mumbai, Maharashtra, 400076, India · Department of Mechanical and Aerospace Engineering, Monash University, Clayton 3800, Victoria, Australia · IITB-Monash Research Academy, Mumbai, Maharashtra, 400076, India +1
Causal Structure is Inducible but Functionally Decoupled: The Routing/Readout Boundary of a Typed Mechanism Library
Aug 12, 2026Xining XunCausal Representation Learning LLM Auditing
Tsingjiao Information Science (Beijing) Co., Ltd.
DiagLoop: A Counterfactual Data Flywheel with Stage-Localized Reinforcement for Diagnostic LLMs
Aug 4, 2026Jian Zhang, Bingyi Wang, Yizhi LiuRL for Language Model Reasoning Causal Reasoning in Language Models
Zhejiang University
CausalOPD: First-Wrong-Step Supervision for Distilling Causal Chain Reasoning
Aug 4, 2026Jian Zhang, Bingyi Wang, Yizhi LiuCurriculum RL Causal Reasoning in Language Models
Zhejiang University
When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs
Aug 4, 2026Omatharv Bharat Vaidya, Connor Thomas Jerzak, Zayne Rea Sprague +2Self-Consistency Decoding Symbolic Reasoning
The University of Texas at Austin · New York University
Evidence-Type Competition: When Can Interventional Data Teach Language Models Causal Direction?
Jul 31, 2026Xining XunCausal Discovery Causal Reasoning in Language Models
Tsingjiao Information Science (Beijing) Co., Ltd.
Same Evidence, Different Target: Decoding How Diagnostic Evidence Bears on Causal Questions from Language-Model States
Jul 29, 2026Weiyi Kong, Zhuoran LiCausal Reasoning in Language Models Causal Inference
University of Toronto, Toronto, Canada · The University of Hong Kong, Hong Kong
Encoding Invisible Causation for Bridge Diagnostic Agents: Triple-Guided Retrieval-Augmented Fine-Tuning with QLoRA
Jul 23, 2026Takato YasunoCausal Attribution Low-Rank Adaptation
CASE: Causal Alignment and Structural Enforcement for Improving Chain-of-Thought Faithfulness
Jul 21, 2026Ziming Wang, Yinghua Yao, Changwu Huang +2CoT Faithfulness Faithfulness of Language Model Explanations
Department of Computer Science and Engineering of Southern University of Science and Technology, Shenzhen, China · Center for Frontier AI Research, Agency for Science, Technology and Research (A*STAR), Singapore · School of AI and Liberal Arts, Beijing Normal-Hong Kong Baptist University, Zhuhai, China +1
PertReason: A Knowledge-Grounded Benchmark and Framework for Cell-State-Conditioned Mechanistic Reasoning of Perturbation Effects
Jul 21, 2026Dongkwan Kim, Yiming Gao, Yining Yang +1LLM Grounding Single-Cell Perturbation Modeling
Department of Electrical and Computer Engineering, Texas A&M University
For What Reason? Interpreting Models' Encoding of Causation and Antithesis
Jul 20, 2026Abhidip Bhattacharyya, Shira WeinTransformer Interpretability Causal Reasoning in Language Models
University of Massachusetts Amherst · University of South Florida
An Explicit World Model Based on Data-First Ontology: DaoQL Multimodal Storage Validation and Counterfactual Reasoning Evaluation
Jul 19, 2026Zhanbo Li, Shifeng Wu, Xiangjin Meng +1LLM Grounding Counterfactual Reasoning in Language Models
Graduate Students, School of Mathematics and Statistics, Chongqing University · DaoQL Project Group · Guangzhou Polytechnic Normal University
WorkDrive: Roadwork Chain of Causation for Autonomous Driving
Jul 16, 2026Tianyi Jiang, Wen Zhang, Sihan Yang +2VLMs for Autonomous Driving Autonomous Driving Perception
Peking University · Beijing, China · Xiaomi EV
Analogical Deep Research: Retrieving and Integrating Historical Analogies for Foresight Analysis
Jul 15, 2026Yongqiang Chen, Guangyi Chen, Yuewen Sun +1Analogical Reasoning LLM Agent Evaluation
1Mohamed bin Zayed University of Artificial Intelligence · 2Carnegie Mellon University
CausalDS: Benchmarking Causal Reasoning in Data-Science Agents
Jul 9, 2026Andrej Leban, Yuekai SunStructural Causal Models AI Agent Benchmarks
Department of Statistics University of Michigan Ann Arbor, MI, United States
CausalGame: Benchmarking Causal Thinking of LLM Agents in Games
Jul 5, 2026Zhenhao Chen, Yongqiang Chen, Chenxi Liu +7AI Agents for Scientific Discovery AI Agent Benchmarks
1MBZUAI · 2Carnegie Mellon University · 3TMLR Group, Hong Kong Baptist University +2
OpenRCA 2.0: From Outcome Labels to Causal Process Supervision
Jun 25, 2026Aoyang Fang, Yifan Yang, Jin'ao Shang +7LLM Agent Evaluation Causal Attribution
The Chinese University of Hong Kong, Shenzhen · Lero · The Chinese University of Hong Kong
When Helpfulness Overrides Causal Caution: Context-Dependent Suppression and Recovery in LLMs
Jun 23, 2026Hiroshi OkumuraLLM Auditing Pragmatic Reasoning in Language Models
Mitsubishi Research Institute, Inc. · Kobe University
Words as Difference Makers: How Large Language Models Determine Causal Structure in Text
Jun 21, 2026Wolfgang PietschCausal World Models LLM Interpretability
tum
ARIA: A Causal-Aware Framework for Rescuing LLM Reasoning in Trustworthy Materials Discovery
Jun 21, 2026Yi Cao, Liaoyaqi Wang, Jieneng Chen +3Knowledge Augmentation for Language Models Materials Property Prediction
Local Causal Attribution of Chain-of-Thought Reasoning
Jun 20, 2026Dennis Wei, Yannis Belkhiter, Erik Miehling +1LLM Interpretability Causal Attribution
1IBM Research.
Vernier: Probing Representational Misalignment Behind Lexical Gaps in Causal Reasoning
Jun 14, 2026Zhenyu YuLLM Interpretability Causal Reasoning in Language Models
College of Computer Science and Artificial Intelligence Fudan University
Reasoning as Pattern Matching: Shared Mechanisms in Human and LLM Everyday Reasoning
Jun 11, 2026Zach Studdiford, Gary LupyanCognitive Modeling LLM Interpretability
University of Wisconsin–Madison Department of Psychology Department of Computer Science

Oct 4, 2026, cs.AIJ/K move · Enter open · S save

Readable Before Actionable: Causal Tracing of Indirect Prompt Injection

Zhe Yu, Wenpeng Xing, Xingxing Yang, Meng Han

Zhejiang University · Binjiang Institute of Zhejiang University · Hong Kong Baptist University

Causal Reasoning in Language Models Indirect Prompt Injection Prompt Injection Defense Prompt Injection Attacks on LLMs Prompt Injection Attacks on AI Agents Causal Interventions in Language Models

Open paper AskPDF arXiv

Indirect prompt injection causes LLM agents to follow commands embedded in external data. A probe may distinguish instructions from data without identifying a state edit that changes the next action. We study this gap through counterfactual role probes, component-wise activation patching, and separate interventions on AgentDojo trajectories. Role decoding survives changes in content and format. In controlled Qwen tests, it precedes strong tool-choice effects from patches along an independently estimated role direction. On AgentDojo, directions estimated from hijacked and resisted training trajectories reduce attack success at pre-action and injected-span positions, but have little effect at random positions. In longer Qwen trajectories, single-position edits become less effective at later layers; span-wide and repeated edits reduce attack success on the same evaluation set. Removing the learned channel subspace preserves role decoding, yet effective intervention directions transfer poorly across the tested channels. These findings distinguish a readable role signal from an effective behavioral intervention: depth matters in controlled tool choice, while position and context also matter in attack trajectories.

Momentum

Related topics

Latest papers 57