# Knowledge Generation for Zero-shot Knowledge-based VQA

Source: [Knowledge Generation for Zero-shot Knowledge-based VQA](<https://www.sota2.com/research/paper/68fa72121e209131cea544f8>)

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

Data updated: 2025-10-26T02:17:23.201Z

Authors: Rui Cao, Jing Jiang

Published: 2024-02-04T15:41:35.000Z

## Abstract

Previous solutions to knowledge-based visual question answering~(K-VQA) retrieve knowledge from external knowledge bases and use supervised learning to train the K-VQA model. Recently pre-trained LLMs have been used as both a knowledge source and a zero-shot QA model for K-VQA and demonstrated promising results. However, these recent methods do not explicitly show the knowledge needed to answer the questions and thus lack interpretability. Inspired by recent work on knowledge generation from LLMs for text-based QA, in this work we propose and test a similar knowledge-generation-based K-VQA method, which first generates knowledge from an LLM and then incorporates the generated knowledge for K-VQA in a zero-shot manner. We evaluate our method on two K-VQA benchmarks and found that our method performs better than previous zero-shot K-VQA methods and our generated knowledge is generally relevant and helpful.

## 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.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2402.02541>)

[PDF](<https://arxiv.org/pdf/2402.02541.pdf>)
