attention head

Query-Focused Retrieval Heads Improve Long-Context Reasoning and Re-ranking EMNLP 2025 Retrieval Head Mechanistically Explains Long-Context Factuality ICLR 2025 Revealing the Deceptiveness of Knowledge Editing: A Mechanistic Analysis of Superficial Editing ACL 2025 SEAL: Scaling to Emphasize Attention for Long-Context Retrieval ACL 2025 Semantics-Adaptive Activation Intervention for LLMs via Dynamic Steering Vectors ICLR 2025 Short-circuiting Shortcuts: Mechanistic Investigation of Shortcuts in Text Classification CoNLL 2025 SparseMM: Head Sparsity Emerges from Visual Concept Responses in MLLMs ICCV 2025 Sparse Video-Gen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity ICML 2025 Steering Prepositional Phrases in Language Models: A Case of with-headed Adjectival and Adverbial Complements in Gemma-2 EMNLP 2025 Structured Pruning for Diverse Best-of-N Reasoning Optimization ACL 2025 Taming Knowledge Conflicts in Language Models ICML 2025 The Validation Gap: A Mechanistic Analysis of How Language Models Compute Arithmetic but Fail to Validate It EMNLP 2025 ThinkEdit: Interpretable Weight Editing to Mitigate Overly Short Thinking in Reasoning Models EMNLP 2025 Time Course MechInterp: Analyzing the Evolution of Components and Knowledge in Large Language Models ACL 2025 Toward Inclusive Language Models: Sparsity-Driven Calibration for Systematic and Interpretable Mitigation of Social Biases in LLMs EMNLP 2025 Understanding and Controlling Repetition Neurons and Induction Heads in In-Context Learning IJCNLP 2025 Unveiling Visual Perception in Language Models: An Attention Head Analysis Approach CVPR 2025 Update Your Transformer to the Latest Release: Re-Basin of Task Vectors ICML 2025 V-SEAM: Visual Semantic Editing and Attention Modulating for Causal Interpretability of Vision-Language Models EMNLP 2025 What Do VLMs NOTICE? A Mechanistic Interpretability Pipeline for Gaussian-Noise-free Text-Image Corruption and Evaluation NAACL 2025 Which Attention Heads Matter for In-Context Learning? ICML 2025 Word Form Matters: LLMs’ Semantic Reconstruction under Typoglycemia ACL 2025 Abrupt Learning in Transformers: A Case Study on Matrix Completion NeurIPS 2024 An Adversarial Example for Direct Logit Attribution: Memory Management in GELU-4L EMNLP 2024 Better Explain Transformers by Illuminating Important Information EACL 2024