Causal Interventions in Language Models

Ask about this topic

Momentum

55 papers in the last four weeks, up 162% on the four weeks before. 0.5% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 317

All topics
CardsList

  1. Amplitude-Only FFN Intervention for Tool-Structured LLM Inference Method: Gated Evaluation Protocol, and Cross-Model Empirical Results

    Jul 13, 2026Sheng Xu, Junhua Wang, Boyuan Huang +3LLM InferenceLLM Tool Use

    Alibaba Cloud

  2. When Are Sparse Feature Interventions Actually Localized? Matched Evaluation for SAE-Based Safety Control

    Jul 11, 2026Daming LuoSparse AutoencodersLLM Safety Evaluation

    University of Technology Sydney

  3. Interventional Grounding Audits: Black-Box Premise-Dependency Tests for LLM Chain-of-Thought via Predicate Substitution

    Jul 11, 2026Hironao NakamuraCoT FaithfulnessLLM Grounding

    Independent Researcher

  4. Certified Interventional Fidelity: Anytime-Valid, Adaptive Evaluation of Causal Claims in Mechanistic Interpretability

    Jul 9, 2026Amir AsiaeeMechanistic InterpretabilityCausal Interventions in Language Models

    Department of Biostatistics, Vanderbilt University Medical Center, Nashville, TN 37232, USA

  5. Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs

    Jul 8, 2026Anupam Wagle, Ifrat Ikhtear Uddin, Chaowei Zhang +1LLM InterpretabilityAdversarial Attacks on LLMs

    Department of Computer Science, University of South Dakota, USA · School of Information and Artificial Intelligence, Yangzhou University, Yangzhou, China

  6. Distributed Sparse Interventions in Language Models

    Jul 8, 2026Maximilian S. Ernst, Lorenz Linhardt, Aaron Peikert +1Language Model SteeringLLM Interpretability

    Max Planck School of Cognition · Center for Lifespan Psychology Max Planck Institute for Human Development · Machine Learning Group Technische Universität Berlin +5

  7. Final Checkpoints Are Not Enough: Analyzing Latent Reasoning Faithfulness Along Training Trajectories

    Jul 7, 2026Hengyu Jin, Shu Yang, Di WangCoT FaithfulnessContinuous Latent Reasoning

    Tongji University · Provable Responsible AI and Data Analytics (PRADA) Lab · King Abdullah University of Science and Technology

  8. Reward Valuation in Large Language Models: Causal Induction of Anhedonia

    Jul 7, 2026Melika Honarmand, Samin Mahdipour Aghabagher, Martin SchrimpfReward ModelingCognitive Modeling

    NeuroAI Laboratory, EPFL

  9. Controlling Tool Use with Heading-Specific Activation Steering

    Jul 7, 2026Yuqi Chen, Vincent Siu, Yang Liu +2Language Model SteeringLLM Tool Use

    Department of Computer Science and Engineering, UC Santa Cruz · Department of Computer Science, UC Berkeley

  10. A Coin Flip Per Token: Bernoulli Sparse Steering of Large Language Models

    Jul 6, 2026Nima Eshraghi, Lovedeep Gondara, Yuqing Huang +5Language Model SteeringSparse Autoencoders

    1The Vanguard Group, Inc. · University of Toronto

  11. Faithfulness to Refusal: A Causal Audit of Neuron Selectors

    Jul 6, 2026Ananth Eswar, Pratinav Seth, Utsav Avaiya +1Transformer InterpretabilityFeature Attribution

    Lexsi Labs · Work done while at Lexsi Labs.

  12. Wrong Before Right: Late Rescue and Interface Failure in Aligned Language Models

    Jul 6, 2026Jiaqi DengLLM AlignmentLLM Interpretability

    Independent Researcher

  13. Transplanting, inverting, and preventing a misalignment persona: method-conditional emergent misalignment in Qwen2.5

    Jul 5, 2026Lyndon Drake, Zandi EberstadtLLM AlignmentLLM Fine-Tuning

    University of Oxford

  14. Can Dialects Be Steered Like Languages? Sparse Neurons and Distributed Directions in Arabic LLMs

    Jul 4, 2026Kareem Elozeiri, Mervat Abassy, Omar Kallas +4Arabic NLPLLM Interpretability

    1Mohamed bin Zayed University of Artificial Intelligence · 2Qatar Computing Research Institute, Hamad Bin Khalifa University · 3Tohoku University +1

  15. Conditional Co-Ablation: Recovering Self-Repair Backups in Transformer Circuits

    Jul 2, 2026Zhiren Gong, He Lu, Tiantong Wang +6Circuit DiscoveryMechanistic Interpretability

    College of Computing and Data Science, Nanyang Technological University, Singapore · Interdisciplinary Graduate Programme, Nanyang Technological University, Singapore · School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore

  16. Auditing Forgetting in Limited Memory Language Models

    Jul 1, 2026Arya Raeesi, Hanna RoedMemory-Augmented Language ModelsLLM Auditing

    University of California, Berkeley, Berkeley, California, United States of America.

  17. Readable but Not Controllable: Neuron-Level Evidence for Medical LLM Hallucination

    Jun 30, 2026Vijay Vankadaru, Asha Matthews, Tanya Roosta +1LLM Hallucination MitigationLLM Interpretability

    School of Information University of California, Berkeley California, USA

  18. Curvature-Guided Module Localization for Low-Rank Detoxification of Backdoored Large Language Models

    Jun 29, 2026Arash Raftari, Mehrdad Mahdavi, Nathan Blackthorn +1LLM Backdoor AttacksBackdoor Defense in LLMs

    AIVault Inc. Orlando, USA

  19. Mechanistically Eliciting Latent Behaviors in Language Models

    Jun 28, 2026Andrew Mack, Nina Panickssery, Alexander Matt TurnerLLM AlignmentLanguage Model Safety Evaluation

    †Principles of Intelligence · ‡Anthropic · §Independent

  20. Do Models Read What They Write? Causal Registers in Scratchpad Reasoning

    Jun 28, 2026Benjamin Shih, John Winnicki, Eric DarveCoT FaithfulnessCoT Reasoning

    Institute for Computational and Mathematical Engineering Stanford University

  21. Invariant Reasoning Directions in Latent Trajectories of Language Models

    Jun 28, 2026Arun Vignesh Malarkkan, Manan Roy Choudhury, Utkarsh Byahut +3Reasoning Consistency in Language ModelsImplicit Reasoning in Language Models

    Arizona State University, Tempe, Arizona.

  22. Mechanistic Personality Analysis of LLMs Steering Personality via Latent Feature Interventions

    Jun 27, 2026David Courtis, Ting HuLanguage Model SteeringLLM Interpretability

    Department of Computing, Queen’s University Kingston, Kingston, ON, Canada.

  23. Forecasting With LLMs: Improved Generalization Through Feature Steering

    Jun 25, 2026Humzah Merchant, Bradford LevyLanguage Model SteeringLLM Interpretability

    University of Chicago, Illinois, United States.

  24. Refusal Lives Downstream of Persona in Chat Models

    Jun 24, 2026Viola Zhong, Qirui LiLanguage Model SteeringLLM Refusal Behavior

    Independent · Department of Mathematics Pohang University of Science and Technology

  25. How Modular Is a Frontier Mixture-of-Experts? A Pre-registered Causal Test in Which Apparent Expert Modularity Mostly Dissolves

    Jun 23, 2026Tony Salomone, Deep Gandhi, Ali AsariaSparse Mixture-of-ExpertsMixture-of-Experts Models

    Transformer Lab

  26. Perfect Detection, Failed Control: The Geometry of Knowing vs. Steering in Language Models

    Jun 23, 2026Cosimo Galeone, Anna Ettorre, Minsu Park +2Mechanistic InterpretabilityCausal Interventions in Language Models

    Alomana, Grottaglie, Italy

  27. First-Token Broadcasters: Mechanistic Origins of Language Identity and Distributed Robustness in Transformers

    Jun 21, 2026Arjun Pillai, Christian Hoang, Anjelo Jann LarozaMultilingual Language ModelsLLM Interpretability

    1Irvington High School · 2GenAI4E · 3Mapua University

  28. Curiosity as Linguistic Intervention: Using LLM Tutoring Dialogues to Influence Exploratory Learning Behavior

    Jun 21, 2026Gevindu Ganganath, Pasindu Bolonghege, Qianru Lyu +2Intelligent Tutoring SystemsIntrinsic Motivation

    School of Computing and Information Systems, Singapore Management University · Human-Computer Interaction Institute, Carnegie Mellon University

  29. Can Reasoning Models Detect Changes to their Chains of Thought?

    Jun 20, 2026Sathvik Napa, Utkarsh Singh, Chengyuan Xue +2Causal Interventions in Language ModelsMetacognition in Language Models

    Johns Hopkins University

  30. A Validation-Gated Mechanistic Account of Suicidality Detection in LLMs

    Jun 19, 2026Nafiz Ahmed, Sarah Sharif, Dingjing Shi +1LLM InterpretabilityMental Health

    Intelligent Neuromorphic and Quantum Understanding for Innovative Research and Engineering (INQUIRE) Lab, School of Electrical and Computer Engineering, University of Oklahoma, Norman, 73019, Oklahoma, U.S.A. · School of Psychology, Georgia Institute of Technology, Atlanta, 30332, Georgia, U.S.A.