|国家预印本平台
首页|Temporal Insight Enhancement: Mitigating Temporal Hallucination in Multimodal Large Language Models

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

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

来源:Arxiv_logoArxiv
英文摘要

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.

Takayuki Okatani、Jun Sun、Liuan Wang、Li Sun

计算技术、计算机技术

Takayuki Okatani,Jun Sun,Liuan Wang,Li Sun.Temporal Insight Enhancement: Mitigating Temporal Hallucination in Multimodal Large Language Models[EB/OL].(2024-01-18)[2025-07-19].https://arxiv.org/abs/2401.09861.点此复制

评论