Clue and Reasoning Prompting

A prompt engineering strategy for large language models that instructs the model to first identify textual clues (keywords, phrases, contextual information) in the input and then perform diagnostic reasoning based on those clues before producing a classification output. Originally designed for sentiment classification, CARP has been adapted for accessibility applications such as jointly classifying user reviews by aspect (e.g., food quality, customer service) and sentiment (positive, negative). The explicit reasoning step improves classification accuracy by making the model's decision process more transparent and grounded in evidence from the text.