Multimodal LLMs, especially GPT-4o and Gemini, can infer plausible Stack Overflow questions from code and IDE screenshots with moderate similarity to the original posts, but performance drops on complex screenshots.
Research update: Improving the question - asking experience
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Inferring Questions from Programming Screenshots
Multimodal LLMs, especially GPT-4o and Gemini, can infer plausible Stack Overflow questions from code and IDE screenshots with moderate similarity to the original posts, but performance drops on complex screenshots.