conftrace_

attention weight

68 papers

Explore in graph

Co-occurring keywords

attention mechanism (4001) neural network (6616) model interpretability (519) text classification (6793) large language model (13587) transformer model (1996) language model (4599) graph neural network (3962) retrieval-augmented generation (1592) feature attribution (280)

Papers

Attention Weights as an Indicator: Analyzing and Improving Document Utilization in Retrieval-Augmented Generation ACL 2026
Ghost in the Transformer: Detecting Model Reuse with Invariant Spectral Signatures AAAI 2026
Detection of Adversarial Prompts with Model Predictive Entropy EACL 2026
EyeMulator: Improving Code Language Models by Mimicking Human Visual Attention ACL 2026
Polysemy Interpretation and Transformer Language Models: A Case of Korean Adverbial Postposition -(u)lo COLING 2025
Masking in Multi-hop QA: An Analysis of How Language Models Perform with Context Permutation ACL 2025
Learning Production Functions for Supply Chains with Graph Neural Networks AAAI 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
Enhancing Elusive Clues in Knowledge Learning by Contrasting Attention of Language Models AAAI 2025
PECAN: LLM-Guided Dynamic Progress Control with Attention-Guided Hierarchical Weighted Graph for Long-Document QA ACL 2025
Attention with Dependency Parsing Augmentation for Fine-Grained Attribution ACL 2025
Mitigate Position Bias in LLMs via Scaling a Single Hidden States Channel ACL 2025
SAFR: Neuron Redistribution for Interpretability NAACL 2025
DeMo: Decoupled Feature-Based Mixture of Experts for Multi-Modal Object Re-Identification AAAI 2025
DHGCN: Dynamic Hop Graph Convolution Network for Self-Supervised Point Cloud Learning AAAI 2024
Learning Visual Body-Shape-Aware Embeddings for Fashion Compatibility WACV 2024
Prompt Highlighter: Interactive Control for Multi-Modal LLMs CVPR 2024
Learning a Spiking Neural Network for Efficient Image Deraining IJCAI 2024
Token Transformation Matters: Towards Faithful Post-hoc Explanation for Vision Transformer CVPR 2024
Contextualized Sequence Likelihood: Enhanced Confidence Scores for Natural Language Generation EMNLP 2024
Tree-Planted Transformers: Unidirectional Transformer Language Models with Implicit Syntactic Supervision ACL 2024
BAM! Just Like That: Simple and Efficient Parameter Upcycling for Mixture of Experts NIPS 2024
An Eye Opener Regarding Task-Based Text Gradient Saliency ACL 2024
Transformers as Graph-to-Graph Models EMNLP 2023