conftrace_

mechanistic interpretability

133 papers

Explore in graph

Also known as

MI

Co-occurring keywords

large language model (13587) language model (4599) sparse autoencoder (112) attention head (146) neural network (6616) circuit analysis (17) in-context learning (1405) circuit discovery (14) attention mechanism (4001) activation patching (23)

Papers

GKnow: Measuring the Entanglement of Gender Bias and Factual Gender ACL 2026

Factual Retrieval in LLMs Is a Redundant, Distributed and Non-Contiguous Process ACL 2026

I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders AAAI 2026

From Insight to Action: A Novel Framework for Interpretability-Guided Data Selection in Large Language Models ACL 2026

Unlocking the Black Box of Latent Reasoning: An Interpretability-Guided Approach to Intervention ACL 2026

Constructing Interpretable Features from Compositional Neuron Groups ACL 2026

How Do LLMs Generate Contrastive Sentiments? A Mechanistic Perspective EACL 2026

How Does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding AAAI 2026

Beyond Transcription: Mechanistic Interpretability in ASR AAAI 2026

Mechanistic Interpretability Should Prioritize Feature Consistency in Sparse Autoencoders ACL 2026

Uncovering Sentiment Analysis Circuit in Large Language Model ACL 2026

Understanding Emergent Misalignment via Feature Superposition Geometry ACL 2026

Why Does Reinforcement Learning Generalize? A Feature-Level Mechanistic Study of Post-Training in Large Language Models ACL 2026

Mechanisms of Prompt-Induced Hallucination in Vision–Language Models ACL 2026

Measuring Mechanistic Independence: Can Bias Be Removed Without Erasing Demographics? EACL 2026

Where Do LLMs Compose Meaning? A Layerwise Analysis of Compositional Robustness EACL 2026

Simplifying Outcomes of Language Model Component Analyses with ELIA EACL 2026

Causal Tracing of Object Representations in Large Vision Language Models: Mechanistic Interpretability and Hallucination Mitigation AAAI 2026

SOM Directions Are Better than One: Multi-Directional Refusal Suppression in Language Models AAAI 2026

Efficient Transcoder Adaptation for Fine-Tuned Models: Revealing Medical Reasoning Mechanisms in Large Language Models AAAI 2026

Beyond I’m Sorry, I Can’t: Dissecting Large-Language-Model Refusal AAAI 2026

Quantifying Aleatoric Uncertainty of In-Context Learning for Robust Measure of LLM Prediction Confidence ACL 2026

Patches of Nonlinearity: Instruction Vectors in Large Language Models ACL 2026

Towards a Mechanistic Understanding of Large Reasoning Models: A Survey of Training, Inference, and Failures ACL 2026

Cell-Based Representation of Relational Binding in Language Models ACL 2026