A two-call prompt that adds pragmatic analysis and reflection improves GPT-4o's sarcasm detection on MUStARD and SemEval2018, but the effect is not consistent across models and lacks statistical validation.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Pragmatic Metacognitive Prompting Improves LLM Performance on Sarcasm Detection
A two-call prompt that adds pragmatic analysis and reflection improves GPT-4o's sarcasm detection on MUStARD and SemEval2018, but the effect is not consistent across models and lacks statistical validation.