mechanistic interpretability

Mechanistic Analysis Of Universality: Numerical Comparison Circuits Across Transformer Architectures ACL 2026 Mechanistic Interpretability of Animacy Effects on Structure Choice in GPT-2 CoNLL 2026 Mechanistic Interpretability Should Prioritize Feature Consistency in Sparse Autoencoders ACL 2026 Patches of Nonlinearity: Instruction Vectors in Large Language Models ACL 2026 Preference Heads in Large Language Models: A Mechanistic Framework for Interpretable Personalization ACL 2026 Quantifying Aleatoric Uncertainty of In-Context Learning for Robust Measure of LLM Prediction Confidence ACL 2026 Simplifying Outcomes of Language Model Component Analyses with ELIA EACL 2026 SOM Directions Are Better than One: Multi-Directional Refusal Suppression in Language Models AAAI 2026 Spectra: A Mechanistic Interpretability Library for Vision-Language Models ACL 2026 Sycophantic Anchors: Localizing and Quantifying User Agreement in Reasoning Models ACL 2026 Towards a Mechanistic Understanding of Large Reasoning Models: A Survey of Training, Inference, and Failures ACL 2026 Uncovering Sentiment Analysis Circuit in Large Language Model ACL 2026 Understanding Counting Mechanisms in Large Language and Vision-Language Models CVPR 2026 Understanding Emergent Misalignment via Feature Superposition Geometry ACL 2026 Unlocking the Black Box of Latent Reasoning: An Interpretability-Guided Approach to Intervention ACL 2026 Where Do LLMs Compose Meaning? A Layerwise Analysis of Compositional Robustness EACL 2026 Why Does Reinforcement Learning Generalize? A Feature-Level Mechanistic Study of Post-Training in Large Language Models ACL 2026 Adaptive Transformer Programs: Bridging the Gap Between Performance and Interpretability in Transformers ICLR 2025 Addition in Four Movements: Mapping Layer-wise Information Trajectories in LLMs EMNLP 2025 All for One: LLMs Solve Mental Math at the Last Token With Information Transferred From Other Tokens EMNLP 2025 Anchored Answers: Unravelling Positional Bias in GPT-2’s Multiple-Choice Questions ACL 2025 Arithmetic Without Algorithms: Language Models Solve Math with a Bag of Heuristics ICLR 2025 A Simple Yet Effective Method for Non-Refusing Context Relevant Fine-grained Safety Steering in LLMs EMNLP 2025 A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models EMNLP 2025 Behavioural vs. Representational Systematicity in End-to-End Models: An Opinionated Survey ACL 2025