attention weight

Attention Weights as an Indicator: Analyzing and Improving Document Utilization in Retrieval-Augmented Generation ACL 2026 Detection of Adversarial Prompts with Model Predictive Entropy EACL 2026 EyeMulator: Improving Code Language Models by Mimicking Human Visual Attention ACL 2026 Ghost in the Transformer: Detecting Model Reuse with Invariant Spectral Signatures AAAI 2026 PAS: Prelim Attention Score for Detecting Object Hallucinations in Large Vision-Language Models CVPR 2026 Unified Spatiotemporal Token Compression for Video-LLMs at Ultra-Low Retention CVPR 2026 Attention with Dependency Parsing Augmentation for Fine-Grained Attribution ACL 2025 DeMo: Decoupled Feature-Based Mixture of Experts for Multi-Modal Object Re-Identification AAAI 2025 Enhancing Elusive Clues in Knowledge Learning by Contrasting Attention of Language Models AAAI 2025 ERICT: Enhancing Robustness by Identifying Concept Tokens in Zero-Shot Vision Language Models ICML 2025 Learning Production Functions for Supply Chains with Graph Neural Networks AAAI 2025 Masking in Multi-hop QA: An Analysis of How Language Models Perform with Context Permutation ACL 2025 Mitigate Position Bias in LLMs via Scaling a Single Hidden States Channel ACL 2025 PECAN: LLM-Guided Dynamic Progress Control with Attention-Guided Hierarchical Weighted Graph for Long-Document QA ACL 2025 Polysemy Interpretation and Transformer Language Models: A Case of Korean Adverbial Postposition -(u)lo COLING 2025 Revealing and Mitigating Over-Attention in Knowledge Editing ICLR 2025 SAFR: Neuron Redistribution for Interpretability NAACL 2025 SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers ACL 2025 Unveiling Visual Perception in Language Models: An Attention Head Analysis Approach CVPR 2025 An Eye Opener Regarding Task-Based Text Gradient Saliency ACL 2024 BAM! Just Like That: Simple and Efficient Parameter Upcycling for Mixture of Experts NeurIPS 2024 Contextualized Sequence Likelihood: Enhanced Confidence Scores for Natural Language Generation EMNLP 2024 Dense Reward for Free in Reinforcement Learning from Human Feedback ICML 2024 DHGCN: Dynamic Hop Graph Convolution Network for Self-Supervised Point Cloud Learning AAAI 2024 Learning a Spiking Neural Network for Efficient Image Deraining IJCAI 2024