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

• URL: http://arxiv.org/abs/2407.15346v1
• Date: Mon, 22 Jul 2024 03:05:32 GMT
• Title: Knowledge Acquisition Disentanglement for Knowledge-based Visual Question Answering with Large Language Models
• Authors: Wenbin An, Feng Tian, Jiahao Nie, Wenkai Shi, Haonan Lin, Yan Chen, QianYing Wang, Yaqiang Wu, Guang Dai, Ping Chen,
• Abstract summary: 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) We propose DKA: Disentangled Knowledge Acquisition from LLM feedback, a training-free framework that disentangles knowledge acquisition to avoid confusion.
• Score: 10.526705722339775
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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}.

Related papers

• Untangle the KNOT: Interweaving Conflicting Knowledge and Reasoning Skills in Large Language Models [51.72963030032491]
  Knowledge documents for large language models (LLMs) may conflict with the memory of LLMs due to outdated or incorrect knowledge. We construct a new dataset, dubbed KNOT, for knowledge conflict resolution examination in the form of question answering.
  arXiv  Detail & Related papers  (2024-04-04T16:40:11Z)
• GeReA: Question-Aware Prompt Captions for Knowledge-based Visual Question Answering [37.11794716736831]
  We argue that multimodal large language model (MLLM) is a better implicit knowledge engine than the large language model (LLM) for its superior capability of visual understanding. We propose GeReA, a generate-reason framework that prompts a MLLM like InstructBLIP with question relevant vision and language information to generate knowledge-relevant descriptions. Specifically, the question-relevant image regions and question-specific manual prompts are encoded in the MLLM to generate the knowledge relevant descriptions.
  arXiv  Detail & Related papers  (2024-02-04T14:28:23Z)
• RECALL: A Benchmark for LLMs Robustness against External Counterfactual Knowledge [69.79676144482792]
  This study aims to evaluate the ability of LLMs to distinguish reliable information from external knowledge. Our benchmark consists of two tasks, Question Answering and Text Generation, and for each task, we provide models with a context containing counterfactual information.
  arXiv  Detail & Related papers  (2023-11-14T13:24:19Z)
• DIVKNOWQA: Assessing the Reasoning Ability of LLMs via Open-Domain Question Answering over Knowledge Base and Text [73.68051228972024]
  Large Language Models (LLMs) have exhibited impressive generation capabilities, but they suffer from hallucinations when relying on their internal knowledge. Retrieval-augmented LLMs have emerged as a potential solution to ground LLMs in external knowledge.
  arXiv  Detail & Related papers  (2023-10-31T04:37:57Z)
• Self-Knowledge Guided Retrieval Augmentation for Large Language Models [59.771098292611846]
  Large language models (LLMs) have shown superior performance without task-specific fine-tuning. Retrieval-based methods can offer non-parametric world knowledge and improve the performance on tasks such as question answering. Self-Knowledge guided Retrieval augmentation (SKR) is a simple yet effective method which can let LLMs refer to the questions they have previously encountered.
  arXiv  Detail & Related papers  (2023-10-08T04:22:33Z)
• Knowledge Solver: Teaching LLMs to Search for Domain Knowledge from Knowledge Graphs [19.0797968186656]
  Large language models (LLMs) are versatile and can solve different tasks due to their emergent ability and generalizability. In some previous works, additional modules like graph neural networks (GNNs) are trained on retrieved knowledge from external knowledge bases.
  arXiv  Detail & Related papers  (2023-09-06T15:55:01Z)
• Prophet: Prompting Large Language Models with Complementary Answer Heuristics for Knowledge-based Visual Question Answering [30.858737348472626]
  Knowledge-based visual question answering (VQA) requires external knowledge beyond the image to answer the question. Recent works have resorted to using a powerful large language model (LLM) as an implicit knowledge engine to acquire the necessary knowledge for answering. We present a conceptually simple, flexible, and general framework designed to prompt LLM with answers for knowledge-based VQA.
  arXiv  Detail & Related papers  (2023-03-03T13:05:15Z)
• Structured Knowledge Grounding for Question Answering [0.23068481501673416]
  We propose to leverage the language and knowledge for knowledge based question-answering with flexibility, breadth of coverage and structured reasoning. Specifically, we devise a knowledge construction method that retrieves the relevant context with a dynamic hop. And we devise a deep fusion mechanism to further bridge the information exchanging bottleneck between the language and the knowledge.
  arXiv  Detail & Related papers  (2022-09-17T08:48:50Z)
• KRISP: Integrating Implicit and Symbolic Knowledge for Open-Domain Knowledge-Based VQA [107.7091094498848]
  One of the most challenging question types in VQA is when answering the question requires outside knowledge not present in the image. In this work we study open-domain knowledge, the setting when the knowledge required to answer a question is not given/annotated, neither at training nor test time. We tap into two types of knowledge representations and reasoning. First, implicit knowledge which can be learned effectively from unsupervised language pre-training and supervised training data with transformer-based models.
  arXiv  Detail & Related papers  (2020-12-20T20:13:02Z)
• Knowledge-Routed Visual Question Reasoning: Challenges for Deep Representation Embedding [140.5911760063681]
  We propose a novel dataset named Knowledge-Routed Visual Question Reasoning for VQA model evaluation. We generate the question-answer pair based on both the Visual Genome scene graph and an external knowledge base with controlled programs.
  arXiv  Detail & Related papers  (2020-12-14T00:33:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.