Knowledge Acquisition Disentanglement for Knowledge-based Visual Question Answering with Large Language Models

TL;DR

This paper introduces DKA, a training-free framework that improves knowledge-based visual question answering by disentangling knowledge acquisition and leveraging LLM feedback to generate more precise answers.

Contribution

DKA is a novel, training-free approach that decomposes complex questions into simpler sub-questions for better knowledge retrieval and answer accuracy in KVQA.

Findings

DKA significantly outperforms state-of-the-art models on benchmark datasets.

Disentangling knowledge acquisition reduces confusion and improves answer precision.

Using LLM feedback to guide knowledge retrieval enhances overall performance.

Abstract

Knowledge-based Visual Question Answering (KVQA) requires both image and world knowledge to answer questions. Current methods first retrieve knowledge from the image and external knowledge base with the original complex question, then generate answers with Large Language Models (LLMs). However, since the original question contains complex elements that require knowledge from different sources, acquiring different kinds of knowledge in a coupled manner may confuse models and hinder them from retrieving precise knowledge. Furthermore, the ``forward-only'' answering process fails to explicitly capture the knowledge needs of LLMs, which can further hurt answering quality. To cope with the above limitations, we propose DKA: Disentangled Knowledge Acquisition from LLM feedback, a training-free framework that disentangles knowledge acquisition to avoid confusion and uses LLM's feedback to specify the required knowledge. Specifically, DKA requires LLMs to specify what knowledge they need to answer the question and decompose the original complex question into two simple sub-questions: Image-based sub-question and Knowledge-based sub-question. Then we use the two sub-questions to retrieve knowledge from the image and knowledge base, respectively. In this way, two knowledge acquisition models can focus on the content that corresponds to them and avoid disturbance of irrelevant elements in the original complex question, which can help to provide more precise knowledge and better align the knowledge needs of LLMs to yield correct answers. Experiments on benchmark datasets show that DKA significantly outperforms SOTA models. To facilitate future research, our data and code are available at \url{https://github.com/Lackel/DKA}.