English

Temporal Insight Enhancement: Mitigating Temporal Hallucination in Multimodal Large Language Models

Computer Vision and Pattern Recognition 2024-01-19 v1 Artificial Intelligence

Abstract

Recent advancements in Multimodal Large Language Models (MLLMs) have significantly enhanced the comprehension of multimedia content, bringing together diverse modalities such as text, images, and videos. However, a critical challenge faced by these models, especially when processing video inputs, is the occurrence of hallucinations - erroneous perceptions or interpretations, particularly at the event level. This study introduces an innovative method to address event-level hallucinations in MLLMs, focusing on specific temporal understanding in video content. Our approach leverages a novel framework that extracts and utilizes event-specific information from both the event query and the provided video to refine MLLMs' response. We propose a unique mechanism that decomposes on-demand event queries into iconic actions. Subsequently, we employ models like CLIP and BLIP2 to predict specific timestamps for event occurrences. Our evaluation, conducted using the Charades-STA dataset, demonstrates a significant reduction in temporal hallucinations and an improvement in the quality of event-related responses. This research not only provides a new perspective in addressing a critical limitation of MLLMs but also contributes a quantitatively measurable method for evaluating MLLMs in the context of temporal-related questions.

Keywords

Cite

@article{arxiv.2401.09861,
  title  = {Temporal Insight Enhancement: Mitigating Temporal Hallucination in Multimodal Large Language Models},
  author = {Li Sun and Liuan Wang and Jun Sun and Takayuki Okatani},
  journal= {arXiv preprint arXiv:2401.09861},
  year   = {2024}
}

Comments

7 pages, 7 figures

R2 v1 2026-06-28T14:20:13.762Z