• Home
  • Search
  • Prophet: Prompting Large Language Models With Complementary Answer Heuristics for Knowledge-Based Visual Question Answering.
  • Open Access IconOpen Access
  • Cite Icon8
  • https://doi.org/10.1109/tpami.2025.3562422Copy DOI Icon

Prophet: Prompting Large Language Models With Complementary Answer Heuristics for Knowledge-Based Visual Question Answering.

  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Knowledge-based visual question answering (VQA) requires external knowledge beyond the image to answer the question. Early studies retrieve required knowledge from explicit knowledge bases (KBs), which often introduces irrelevant information to the question, hence restricting the performance of their models. Recent works have resorted to using a powerful large language model (LLM) as an implicit knowledge engine to acquire the necessary knowledge for answering. Despite the encouraging results achieved by these methods, we argue that they have not fully activated the capacity of the LLM as the provided textual input is insufficient to depict the required visual information to answer the question. In this paper, we present Prophet-a conceptually simple, flexible, and general framework designed to prompt LLM with answer heuristics for knowledge-based VQA. Specifically, we first train a vanilla VQA model on a specific knowledge-based VQA dataset without external knowledge. After that, we extract two types of complementary answer heuristics from the VQA model: answer candidates and answer-aware examples. The two types of answer heuristics are jointly encoded into a formatted prompt to facilitate the LLM's understanding of both the image and question, thus generating a more accurate answer. By incorporating the state-of-the-art LLM GPT-3 (Brown et al. 2020), Prophet significantly outperforms existing state-of-the-art methods on four challenging knowledge-based VQA datasets. Prophet is general that can be instantiated with the combinations of different VQA models (i.e., both discriminative and generative ones) and different LLMs (i.e., both commercial and open-source ones). Moreover, Prophet can also be integrated with modern large multimodal models in different stages, which is named Prophet++, to further improve the capabilities on knowledge-based VQA tasks.

Similar Papers
  • Research Article
  • Citations42

Knowledge-Routed Visual Question Reasoning: Challenges for Deep Representation Embedding.

  • Jan 01, 2021
  • IEEE Transactions on Neural Networks and Learning Systems
  • Qingxing Cao +4
  • Research Article
  • Citations41

Prompting large language model with context and pre-answer for knowledge-based VQA

  • Mar 06, 2024
  • Pattern Recognition
  • Zhongjian Hu +3
  • Research Article
  • Citations30

Improving Automatic VQA Evaluation Using Large Language Models

  • Mar 24, 2024
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Oscar Mañas +2
  • Research Article
  • Citations2

LMT++: Adaptively Collaborating LLMs With Multi-Specialized Teachers for Continual VQA in Robotic Surgical Videos.

  • Jan 01, 2025
  • IEEE transactions on medical imaging
  • Yuyang Du +8
  • PDF
  • Conference Article
  • Citations2

Can Pre-training help VQA with Lexical Variations?

  • Jan 01, 2020
  • Shailza Jolly +1
  • Book Chapter
  • Citations6

Generalizing Visual Question Answering from Synthetic to Human-Written Questions via a Chain of QA with a Large Language Model

  • Oct 16, 2024
  • Frontiers in artificial intelligence and applications
  • Taehee Kim +4
  • Research Article
  • Citations1

Adversarial Sample Synthesis for Visual Question Answering

  • Nov 21, 2024
  • ACM Transactions on Multimedia Computing, Communications, and Applications
  • Chuanhao Li +4
  • Conference Article
  • Citations7

Unleashing the Potential of Large Language Model: Zero-shot VQA for Flood Disaster Scenario

  • Nov 17, 2023
  • Yimin Sun +2
  • Research Article

PLMAS: Adaptive Sample Selection for Prompting LLMs in Knowledge-Based Visual Question Answering

  • Nov 19, 2025
  • ACM Transactions on Multimedia Computing, Communications, and Applications
  • Jian Li +4
  • Conference Article
  • Citations668

Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering

  • Jun 01, 2018
  • Aishwarya Agrawal +3
  • PDF
  • Research Article
  • Citations19

Advancing surgical VQA with scene graph knowledge

  • May 23, 2024
  • International Journal of Computer Assisted Radiology and Surgery
  • Kun Yuan +5
  • PDF
  • Research Article
  • Citations5

Visual Question Answering Models for Zero-Shot Pedestrian Attribute Recognition: A Comparative Study

  • Jun 28, 2024
  • SN Computer Science
  • Modesto Castrillón-Santana +5
  • Research Article
  • Citations7

Evaluating the performance of large language & visual-language models in cervical cytology screening

  • May 23, 2025
  • npj Precision Oncology
  • Qi Hong +15
  • Research Article
  • Citations503

Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering

  • Sep 11, 2018
  • International Journal of Computer Vision
  • Yash Goyal +5
  • Conference Article
  • Citations47

Quantifying and Alleviating the Language Prior Problem in Visual Question Answering

  • Jul 18, 2019
  • Yangyang Guo +5
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.