# Empowering Large Language Model for Continual Video Question Answering with Collaborative Prompting

Source: [Empowering Large Language Model for Continual Video Question Answering with Collaborative Prompting](<https://www.sota2.com/research/paper/68fa76961e209131cea6de6f>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T03:57:26.101Z

Authors: Chen Cai, Zheng Wang, Jianjun Gao, Wenyang Liu, Ye Lu, Runzhong Zhang, Kim-Hui Yap

Published: 2024-10-01T15:07:07.000Z

## Abstract

In recent years, the rapid increase in online video content has underscored the limitations of static Video Question Answering (VideoQA) models trained on fixed datasets, as they struggle to adapt to new questions or tasks posed by newly available content. In this paper, we explore the novel challenge of VideoQA within a continual learning framework, and empirically identify a critical issue: fine-tuning a large language model (LLM) for a sequence of tasks often results in catastrophic forgetting. To address this, we propose Collaborative Prompting (ColPro), which integrates specific question constraint prompting, knowledge acquisition prompting, and visual temporal awareness prompting. These prompts aim to capture textual question context, visual content, and video temporal dynamics in VideoQA, a perspective underexplored in prior research. Experimental results on the NExT-QA and DramaQA datasets show that ColPro achieves superior performance compared to existing approaches, achieving 55.14\\% accuracy on NExT-QA and 71.24\\% accuracy on DramaQA, highlighting its practical relevance and effectiveness.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Continual Video Question Answering on NExT-QA (test)](<https://www.sota2.com/research/sota/continual-video-question-answering-on-next-qa-test.md>): Continual Video Question Answering; NExT-QA (test); Accuracy: 55.14.

- [Continual Video Question Answering on DramaQA (test)](<https://www.sota2.com/research/sota/continual-video-question-answering-on-dramaqa-test.md>): Continual Video Question Answering; DramaQA (test); Accuracy: 71.24.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2410.00771>)

[PDF](<https://arxiv.org/pdf/2410.00771.pdf>)