conftrace_

attention calibration

5 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (2) hallucination reduction (2) attention mechanism (2) image token (1) accuracy improvement (1) positional attention bia (1) concept disentanglement (1) inference (1) input-adaptive (1) attention sink (1)

Papers

CAAC: Confidence-Aware Attention Calibration to Reduce Hallucinations in Large Vision-Language Models WACV 2026 Don’t Miss the Forest for the Trees: Attentional Vision Calibration for Large Vision Language Models ACL 2025 Attention Calibration for Disentangled Text-to-Image Personalization CVPR 2024 Found in the middle: Calibrating Positional Attention Bias Improves Long Context Utilization ACL 2024 Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration ICML 2024