Causal Interventions in Language Models

Overview

This field asks which internal states, features, heads, neurons, or context elements actually influence a language model’s decisions, rather than merely correlate with them. Researchers use counterfactual prompt and evidence edits, activation patching and ablation, causal tracing, sparse-autoencoder features, and inference-time steering or weight edits to test mechanisms and control behavior. Applications include checking whether chain-of-thought and retrieved evidence drive answers, and modifying refusal, hallucination, bias, tool use, or reasoning while preserving unrelated capabilities. Results show that readable representations are often not causally used or easily steered; effects vary by layer, task, model, and context, while redundancy and collateral effects make reliable, selective interventions a continuing challenge.

Latest papers

CardsList

532 papers55 papers in the last four weeks, down 37% on the four weeks before. 0.4% of all new papers.

  1. Causal Front-Door Adjustment for Robust Jailbreak Attacks on LLMs

    Feb 5, 2026Yao Zhou, Zeen Song, Wenwen Qiang +2Adversarial Attacks on LLMsLLM Jailbreak Attacks

  2. Towards Isolated Interventions via Almost Orthogonal Features in Language Models

    Feb 4, 2026Moritz Miller, Florent Draye, Bernhard SchölkopfDisentangled Representation LearningRepresentation Learning

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

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

  4. There Is More to Refusal in Large Language Models than a Single Direction

    Feb 2, 2026Faaiz Joad, Majd Hawasly, Sabri Boughorbel +2LLM InterpretabilityLLM Refusal Behavior

  5. Beyond Dense States: Sparse Transcoders as Causally Testable Operators for LLM Latent Reasoning

    Feb 2, 2026Yadong Wang, Haodong Chen, Yu Tian +3Sparse AutoencodersContinuous Latent Reasoning

  6. Cross-Lingual Activation Steering for Multilingual Language Models

    Jan 23, 2026Rhitabrat Pokharel, Ameeta Agrawal, Tanay NagarMultilingual Language ModelsLanguage Model Steering

  7. SteerEval: Inference-time Interventions Strengthen Multilingual Generalization in Neural Summarization Metrics

    Jan 22, 2026Silvia Casola, Ryan Soh-Eun Shim, Felicia Körner +2Summarization EvaluationLanguage Model Steering

  8. Tracing the Latent Threads: A Mechanistic Study of How LLMs Represent and Operationalize Race and Ethnicity Cues

    Jan 19, 2026Shiyue Hu, Ruizhe Li, Yanjun GaoLLM InterpretabilityMechanistic Interpretability

  9. To Copy or Not to Copy: Copying Is Easier to Induce Than Recall

    Jan 17, 2026Mehrdad Farahani, Franziska Penzkofer, Richard JohanssonKnowledge Conflicts in Language ModelsLLM Interpretability

  10. Steering Language Models Before They Speak: Logit-Level Interventions

    Jan 16, 2026Hyeseon An, Shinwoo Park, Hyundong Jin +1Language Model SteeringControllable Text Generation

  11. Triggering Chain-of-Thought via Latent Feature Interventions in Large Language Models

    Jan 12, 2026Zhenghao He, Guangzhi Xiong, Bohan Liu +2LLM InterpretabilityCoT Reasoning

  12. SGM: Safety Glasses for Multimodal Large Language Models via Neuron-Level Detoxification

    Dec 17, 2025Hongbo Wang, AprilPyone MaungMaung, Isao EchizenMLLM SafetyMultimodal Robustness

  13. D-STEER: Two-Way Control of DPO-Induced Safety Behavior in Activation Space

    Dec 3, 2025Samarth Raina, Saksham Aggarwal, Amit Dhanda +3Causal Interventions in Language ModelsActivation Steering

  14. LIFT: Likelihood-Based Intervention Faithfulness Training

    Sep 10, 2025Anand Swaroop, Maheep Chaudhary, Kevin Zhu +2CoT FaithfulnessFaithfulness of Language Model Explanations

  15. LLMs Encode Harmfulness and Refusal Separately

    Jul 16, 2025Jiachen Zhao, Jing Huang, Zhengxuan Wu +2LLM InterpretabilityLLM Refusal Behavior

  16. When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning

    May 21, 2025Rongzhi Zhu, Yi Liu, Jiancheng Wang +6Overthinking in Language ModelsLLM Interpretability

  17. Verbosity Tradeoffs and the Impact of Scale on the Faithfulness of LLM Self-Explanations

    Mar 17, 2025Noah Y. Siegel, Nicolas Heess, Maria Perez-Ortiz +1Faithfulness of Language Model ExplanationsLLM Interpretability