Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ahmed, Faiz, Tan, Xuchen, Adewole, Folajinmi, Datta, Suprakash, Nayebi, Maleknaz
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2504.18912
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913810019778560
author Ahmed, Faiz
Tan, Xuchen
Adewole, Folajinmi
Datta, Suprakash
Nayebi, Maleknaz
author_facet Ahmed, Faiz
Tan, Xuchen
Adewole, Folajinmi
Datta, Suprakash
Nayebi, Maleknaz
contents The integration of generative AI into developer forums like Stack Overflow presents an opportunity to enhance problem-solving by allowing users to post screenshots of code or Integrated Development Environments (IDEs) instead of traditional text-based queries. This study evaluates the effectiveness of various large language models (LLMs), specifically LLAMA, GEMINI, and GPT-4o in interpreting such visual inputs. We employ prompt engineering techniques, including in-context learning, chain-of-thought prompting, and few-shot learning, to assess each model's responsiveness and accuracy. Our findings show that while GPT-4o shows promising capabilities, achieving over 60% similarity to baseline questions for 51.75% of the tested images, challenges remain in obtaining consistent and accurate interpretations for more complex images. This research advances our understanding of the feasibility of using generative AI for image-centric problem-solving in developer communities, highlighting both the potential benefits and current limitations of this approach while envisioning a future where visual-based debugging copilot tools become a reality.
format Preprint
id arxiv_https___arxiv_org_abs_2504_18912
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Inferring Questions from Programming Screenshots
Ahmed, Faiz
Tan, Xuchen
Adewole, Folajinmi
Datta, Suprakash
Nayebi, Maleknaz
Software Engineering
The integration of generative AI into developer forums like Stack Overflow presents an opportunity to enhance problem-solving by allowing users to post screenshots of code or Integrated Development Environments (IDEs) instead of traditional text-based queries. This study evaluates the effectiveness of various large language models (LLMs), specifically LLAMA, GEMINI, and GPT-4o in interpreting such visual inputs. We employ prompt engineering techniques, including in-context learning, chain-of-thought prompting, and few-shot learning, to assess each model's responsiveness and accuracy. Our findings show that while GPT-4o shows promising capabilities, achieving over 60% similarity to baseline questions for 51.75% of the tested images, challenges remain in obtaining consistent and accurate interpretations for more complex images. This research advances our understanding of the feasibility of using generative AI for image-centric problem-solving in developer communities, highlighting both the potential benefits and current limitations of this approach while envisioning a future where visual-based debugging copilot tools become a reality.
title Inferring Questions from Programming Screenshots
topic Software Engineering
url https://arxiv.org/abs/2504.18912