Causal Interpretability

Ask about this topic

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

107 papers7 papers in the last four weeks, down 22% on the four weeks before. 0.0% of all new papers.

  1. Attention Gathers, MLPs Compose: A Causal Analysis of an Action-Outcome Circuit in VideoViT

    Mar 11, 2026Sai V R ChereddyTransformer InterpretabilityVideo Representation Learning

    Independent Researcher

  2. Causal Concept Graphs in LLM Latent Space for Stepwise Reasoning

    Mar 11, 2026Md Muntaqim Meherab, Noor Islam S. Mohammad, Faiza FerozLLM Reasoning with GraphsCausal Interpretability

    Daffodil International University, Dhaka, Bangladesh · New York University, Brooklyn, NY, USA

  3. Interpretable-by-Design Transformers via Architectural Stream Independence

    Mar 8, 2026Clayton Kerce, Alexis FoxTransformer InterpretabilityNeural Network Interpretability

    Georgia Tech Research Institute

  4. Causal Interpretation of Neural Network Computations with Contribution Decomposition

    Mar 6, 2026Joshua Brendan Melander, Zaki Alaoui, Shenghua Liu +2Neural Network InterpretabilityMechanistic Interpretability

    Department of Neurobiology, Stanford University · Department of Physics, Stanford University · Department of Applied Physics, Stanford University

  5. Causal Circuit Tracing Reveals Distinct Computational Architectures in Single-Cell Foundation Models: Inhibitory Dominance, Biological Coherence, and Cross-Model Convergence

    Mar 2, 2026Ihor KendiukhovMechanistic InterpretabilityCausal Interpretability

    Department of Computer Science, University of Tübingen, Tübingen, Germany

  6. CIRCUS: Circuit Consensus under Uncertainty via Stability Ensembles

    Feb 28, 2026Swapnil ParekhCircuit DiscoveryCircuits in Language Models

    Intuit

  7. Inferential Mechanics Part 1: Causal Mechanistic Theories of Machine Learning in Chemical Biology with Implications

    Feb 26, 2026Ilya Balabin, Thomas M. KaiserCausal InterpretabilityStructural Causal Models

    Avicenna Biosciences, Inc., Durham, NC, USA

  8. Leveraging Causal Reasoning Method for Explaining Medical Image Segmentation Models

    Feb 24, 2026Limai Jiang, Ruitao Xie, Bokai Yang +6Explainable Medical Image AnalysisMedical Image Segmentation

    Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences · University of Chinese Academy of Sciences · Shenzhen University of Advanced Technology +3

  9. Causality by Abstraction: Symbolic Rule Learning in Multivariate Timeseries with Large Language Models

    Feb 19, 2026Preetom Biswas, Giulia Pedrielli, K. Selçuk CandanCausal InterpretabilityTime-Series Causal Discovery

    Arizona State University, Tempe, AZ, USA

  10. Causality is Key for Interpretability Claims to Generalise

    Feb 18, 2026Shruti Joshi, Aaron Mueller, David Klindt +3LLM InterpretabilityCausal Interpretability

    Mila - Québec AI Institute & Université de Montréal · Boston University · Cold Spring Harbor Laboratory +1

  11. Activation Steering via Generative Causal Mediation

    Feb 17, 2026Aruna Sankaranarayanan, Amir Zur, Atticus Geiger +1Language Model SteeringCausal Interventions in Language Models

    CSAIL, MIT · Pr(AI)2R · Stanford University +1

  12. A unified framework for evaluating the robustness of machine-learning interpretability for prospect risking

    Feb 16, 2026Prithwijit Chowdhury, Ahmad Mustafa, Mohit Prabhushankar +1Explainability EvaluationExplainable Artificial Intelligence

    Center for Energy and Geo Processing (CeGP), Omni Lab for Intelligent Visual Engineering and Science (OLIVES), School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA.

  13. ReBeCA: Causality-Inspired Behavior Analysis for Understanding the Self-Reflection of Language Models

    Feb 6, 2026Tianqiang Yan, Lizhen Qu, Sihan Shang +6LLM Self-RefinementCausal Interpretability

    Monash University · Harbin Institute of Technology, Shenzhen · Hainan University +2

  14. Bypassing the Rationale: Causal Auditing of Implicit Reasoning in Language Models

    Feb 3, 2026Anish Sathyanarayanan, Aditya Nagarsekar, Aarush RathoreCoT FaithfulnessFaithfulness of Language Model Explanations

    BITS Pilani, K. K. Birla Goa Campus

  15. Attribution Graphs and Causal Probing for Mechanistic Discovery and Bias Repair in Multimodal Generative Learning

    Oct 14, 2025Noor Islam S. Mohammad, Uluğ BayazıtGradient-Based AttributionCausal Representation Learning

    1,2Istanbul Technical University

  16. Quantifying Symptom Causality in Clinical Decision Making: An Exploration Using CausaLM

    Mar 25, 2025Alexander Romanus, Mehul Shetty, Connor JordanClinical Decision-MakingCausal Interpretability

  17. Causal Explanations for Image Classifiers

    Nov 13, 2024Hana Chockler, David A. Kelly, Daniel Kroening +1Actual CausalityExplainable Image Classification

    King’s College London, London, UK · Amazon.com, Inc.,, USA · Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE +1