Overview

Causal interpretability asks not just what information a model represents, but what changes its behavior when that information or a component is altered. Researchers use activation patching and ablation, causal mediation, sparse autoencoders, circuit discovery, and counterfactual feature attribution to trace effects through models. These approaches are applied to language-model reasoning, vision and multimodal systems, and scientific or time-series predictors. A central challenge is showing that an explanation reflects the mechanism used on natural inputs: a feature can be easy to decode without affecting the output, and causal conclusions depend on intervention design, assumptions, and robustness checks.

Latest papers

CardsList

120 papers10 papers in the last four weeks, level with the four weeks before. 0.1% of all new papers.

  1. From Constraints to Causality: Petri net Encodings for Explaining Binary Neural Network Inference

    Nov 17, 2026Alex Chan, Mohamed Tarraf, Alex Yakovlev +1Binary Neural NetworksNeural Network Interpretability

  2. Context Graph: Explainable Multi-Agent Decision Chains in AI-RAN

    Nov 12, 2026Xijun Wang, Zhaoyang Liu, Xiang Chen +2Explainable Artificial IntelligenceAI Agent Auditing

  3. A Mechanistic Interpretability Study of an Astronomy Foundation Model

    Nov 11, 2026Rachel C. Zhang, Alberto Bietti, Wes Gurnee +2Multimodal Model InterpretabilityMechanistic Interpretability

  4. Causal Concept Explanations for Deep Neural Models

    Nov 10, 2026Josh Rountree, Pulkit Verma, Oswin So +2Concept-Based ExplanationsNeural Network Interpretability

  5. Causal discovery from Bayesian symbolic regression

    Nov 9, 2026Roger Guimerà, Kai-Hendrik Cohrs, Sergio Pedreira +2Causal DiscoveryTime-Series Causal Discovery

  6. Understanding AI from the Inside: The State of Mechanistic Interpretability for AI Safety

    Nov 5, 2026Fazl Barez, Tung-Yu Wu, Hunar Batra +24Mechanistic InterpretabilityAI Safety

  7. A Bounded Evaluation Protocol for Representational Systematicity

    Nov 1, 2026Boyu Cao, Wenshuo WangExplainability EvaluationFaithfulness of Language Model Explanations

  8. CausalXRL: Explainable Reinforcement Learning through Causal Graph Reasoning

    Oct 30, 2026Yanming Zhang, Eric Papenhausen, Klaus MuellerInterpretability in RLCausal Interpretability

  9. From Error Prediction to Causal Influence: Auditing SAE Features in Multiple-Choice QA

    Oct 27, 2026Aria Nourbakhsh, Adelaide Danilov, Oleksandr Marchenko Breneur +1Sparse AutoencodersCausal Interpretability

  10. On Reasoning Correctness Directions

    Oct 18, 2026Munachiso Samuel Nwadike, Zayd M. K. Zuhri, Rifo Genadi +5Causal InterpretabilityActivation Steering

  11. World Model Interpretability: From Decoding Representations to Understanding Latent Worlds

    Oct 18, 2026Jize Wang, Yongcheng Jing, Xinyi Le +3World ModelsLatent World Models

  12. Slaying the Hydra: Interaction-Aware Circuit Discovery in Language Models

    Oct 2, 2026Sankaran Vaidyanathan, Rafal Urbaniak, Emily Bunnapradist +2Circuits in Language ModelsMechanistic Interpretability

  13. Capacity, Responsiveness and Alignment: What Makes a Latent Structure Actionable

    Sep 28, 2026Or Shafran, Mor GevaCausal Interventions in Language ModelsCausal Interpretability

  14. What Would Falsify It? A Variable Specific Evidence Standard for Mechanistic Claims About Self Explanation

    Sep 26, 2026Arshia Eftekhari zadehLLM InterpretabilityFaithfulness of Language Model Explanations

  15. Certifying Interventional Agreement Among Observationally Equivalent Causal Models

    Sep 26, 2026Sourena Khanzadeh, Daniel Platnick, Marjan Alirezaie +1Causal InferenceCausal Intervention

  16. Are Stated Reasoning Steps Causally Load-Bearing?

    Sep 22, 2026Abhiram Bhupatiraju, Rayan NyaupaneCoT FaithfulnessLLM Auditing

  17. From Concept Alignment to Causal Grounding: An Intervention Test of Chain-of-Thought Faithfulness

    Sep 19, 2026Qianli Wang, Yilong Wang, Dennis Wei +5CoT FaithfulnessLLM Interpretability

  18. Same Outcome, Different Readout: What Does a Steerable Valence Direction in LLMs Represent?

    Sep 19, 2026Weihan Li, Xinlei Chen, Yuhan Song +2Language Model SteeringLLM Interpretability

  19. Splitting the Difference: Interpretable Causal Forests for Treatment Effect Heterogeneity and Bias

    Sep 15, 2026Nicolas Alexander Ihlo, Merle BehrCausal Effect EstimationConditional Average Treatment Effect Estimation

  20. PhysSAE: Mechanistic Interpretability of PINNs with Sparse Autoencoders

    Sep 7, 2026Nandita N. Patil, Eshwar R. A., Gajanan V. HonnavarMechanistic InterpretabilityCausal Interpretability