# Abduction of Domain Relationships from Data for VQA

Source: [Abduction of Domain Relationships from Data for VQA](<https://www.sota2.com/research/paper/68fa76ee1e209131cea7001e>)

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

Data updated: 2025-10-26T04:06:07.870Z

Authors: Al Mehdi Saadat Chowdhury, Paulo Shakarian, Gerardo I. Simari

Published: 2025-02-13T11:50:04.000Z

## Abstract

In this paper, we study the problem of visual question answering (VQA) where the image and query are represented by ASP programs that lack domain data.  We provide an approach that is orthogonal and complementary to existing knowledge augmentation techniques where we abduce domain relationships of image constructs from past examples. After framing the abduction problem, we provide a baseline approach, and an implementation that significantly improves the accuracy of query answering yet requires few examples.

## 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/2502.09219>)

[PDF](<https://arxiv.org/pdf/2502.09219.pdf>)