attention head

Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination ACL 2026 What Matters to an LLM? Behavioral and Computational Evidences from Summarization EACL 2026 A Closer Look at Backdoor Attacks on CLIP ICML 2025 Align Attention Heads Before Merging Them: An Effective Way for Converting MHA to GQA EMNLP 2025 Analyzing the Rapid Generalization of SFT via the Perspective of Attention Head Activation Patterns ACL 2025 Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions ICLR 2025 Benchmarking and Understanding Compositional Relational Reasoning of LLMs AAAI 2025 Between Circuits and Chomsky: Pre-pretraining on Formal Languages Imparts Linguistic Biases ACL 2025 Beyond Position: the emergence of wavelet-like properties in Transformers ACL 2025 Bias A-head? Analyzing Bias in Transformer-Based Language Model Attention Heads NAACL 2025 CateKV: On Sequential Consistency for Long-Context LLM Inference Acceleration ICML 2025 Context-aware Biases for Length Extrapolation EMNLP 2025 Cooperative or Competitive? Understanding the Interaction between Attention Heads From A Game Theory Perspective ACL 2025 DeCoRe: Decoding by Contrasting Retrieval Heads to Mitigate Hallucinations EMNLP 2025 Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient ICLR 2025 Dissecting Persona-Driven Reasoning in Language Models via Activation Patching EMNLP 2025 Distributional Surgery for Language Model Activations EMNLP 2025 Does Time Have Its Place? Temporal Heads: Where Language Models Recall Time-specific Information ACL 2025 Efficient Automated Circuit Discovery in Transformers using Contextual Decomposition ICLR 2025 Evil twins are not that evil: Qualitative insights into machine-generated prompts EMNLP 2025 From Attention to Activation: Unraveling the Enigmas of Large Language Models ICLR 2025 From Black Boxes to Transparent Minds: Evaluating and Enhancing the Theory of Mind in Multimodal Large Language Models ICML 2025 HeadMap: Locating and Enhancing Knowledge Circuits in LLMs ICLR 2025 Heads up! Large Language Models Can Perform Tasks Without Your Instruction via Selective Attention Head Masking ICML 2025 Hierarchical Safety Realignment: Lightweight Restoration of Safety in Pruned Large Vision-Language Models ACL 2025