Mitigating Hallucination in Large Vision-Language Models via Adaptive Attention Calibration
This addresses the issue of unreliable outputs in vision-language models for users in multimodal AI applications, representing an incremental improvement over existing training-free methods.
The paper tackles the problem of hallucination in large vision-language models, where models incorrectly describe non-existent objects, by introducing the Confidence-Aware Attention Calibration (CAAC) framework, which reduces hallucination and outperforms baselines on benchmarks like CHAIR, AMBER, and POPE, especially in long-form generation scenarios.
Large vision-language models (LVLMs) achieve impressive performance on multimodal tasks but often suffer from hallucination, and confidently describe objects or attributes not present in the image. Current training-free interventions struggle to maintain accuracy in open-ended and long-form generation scenarios. We introduce the Confidence-Aware Attention Calibration (CAAC) framework to address this challenge by targeting two key biases: spatial perception bias, which distributes attention disproportionately across image tokens, and modality bias, which shifts focus from visual to textual inputs over time. CAAC employs a two-step approach: Visual-Token Calibration (VTC) to balance attention across visual tokens, and Adaptive Attention Re-Scaling (AAR) to reinforce visual grounding guided by the model's confidence. This confidence-driven adjustment ensures consistent visual alignment during generation. Experiments on CHAIR, AMBER, and POPE benchmarks demonstrate that CAAC outperforms baselines, particularly in long-form generations, effectively reducing hallucination.