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.
Gemini 1.5 pro model card,
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.