SmartSight: Mitigating Hallucination in Video-LLMs Without Compromising Video Understanding via Temporal Attention Collapse

TL;DR

SmartSight is a training-free method that reduces hallucinations in Video-LLMs by using introspective scoring and attention analysis, improving reliability without sacrificing video understanding.

Contribution

It introduces a novel introspective approach leveraging temporal attention analysis to mitigate hallucinations without retraining the model.

Findings

Reduces hallucinations by 10.59% on VRIPT-HAL

Enhances video understanding and reasoning performance by up to 8.86%

Achieves this with lower decoding costs through early response termination

Abstract

Despite Video Large Language Models having rapidly advanced in recent years, perceptual hallucinations pose a substantial safety risk, which severely restricts their real-world applicability. While several methods for hallucination mitigation have been proposed, they often compromise the model's capacity for video understanding and reasoning. In this work, we propose SmartSight, a pioneering step to address this issue in a training-free manner by leveraging the model's own introspective capabilities. Specifically, SmartSight generates multiple candidate responses to uncover low-hallucinated outputs that are often obscured by standard greedy decoding. It assesses the hallucination of each response using the Temporal Attention Collapse score, which measures whether the model over-focuses on trivial temporal regions of the input video when generating the response. To improve efficiency, SmartSight identifies the Visual Attention Vanishing point, enabling more accurate hallucination estimation and early termination of hallucinated responses, leading to a substantial reduction in decoding cost. Experiments show that SmartSight substantially lowers hallucinations for Qwen2.5-VL-7B by 10.59% on VRIPT-HAL, while simultaneously enhancing video understanding and reasoning, boosting performance on VideoMMMU by up to 8.86%. These results highlight SmartSight's effectiveness in improving the reliability of open-source Video-LLMs.