attention head

How do autoregressive transformers solve full addition? EMNLP 2025 How Do Large Vision-Language Models See Text in Image? Unveiling the Distinctive Role of OCR Heads EMNLP 2025 How Do Transformers Learn Variable Binding in Symbolic Programs? ICML 2025 Improving Contextual Faithfulness of Large Language Models via Retrieval Heads-Induced Optimization ACL 2025 Inferring Functionality of Attention Heads from their Parameters ACL 2025 Interpret and Improve In-Context Learning via the Lens of Input-Label Mappings ACL 2025 Interpreting Language Models Through Concept Descriptions: A Survey EMNLP 2025 Investigating Neurons and Heads in Transformer-based LLMs for Typographical Errors EMNLP 2025 Jailbreak Defense in LLM via Attention Head Analysis and Selective Intervention ACML 2025 Language Models Grow Less Humanlike beyond Phase Transition ACL 2025 Learning Task Representations from In-Context Learning ACL 2025 Learn to Memorize: Scalable Continual Learning in Semiparametric Models with Mixture-of-Neighbors Induction Memory ACL 2025 Linear Representations of Political Perspective Emerge in Large Language Models ICLR 2025 Linguistically Grounded Analysis of Language Models using Shapley Head Values NAACL 2025 Llama See, Llama Do: A Mechanistic Perspective on Contextual Entrainment and Distraction in LLMs ACL 2025 Mechanism and Emergence of Stacked Attention Heads in Multi-Layer Transformers ICLR 2025 Mitigating Hallucinations in Vision-Language Models through Image-Guided Head Suppression EMNLP 2025 Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning ICLR 2025 NoVo: Norm Voting off Hallucinations with Attention Heads in Large Language Models ICLR 2025 On the Role of Attention Heads in Large Language Model Safety ICLR 2025 Option Symbol Matters: Investigating and Mitigating Multiple-Choice Option Symbol Bias of Large Language Models NAACL 2025 Probing and Boosting Large Language Models Capabilities via Attention Heads EMNLP 2025 Pruning the Paradox: How CLIP’s Most Informative Heads Enhance Performance While Amplifying Bias EMNLP 2025 Quality over Quantity in Attention Layers: When Adding More Heads Hurts ICLR 2025 Quantifying Logical Consistency in Transformers via Query-Key Alignment EMNLP 2025