Across 156 configurations on Persian medical board questions, Chain-of-Thought prompting raised accuracy while increasing overconfidence, and emotional prompting inflated confidence without accuracy gains.
Do Language Models Know When They’re Hallucinating References?
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CY 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Evaluating Prompt Engineering Techniques for Accuracy and Confidence Elicitation in Medical LLMs
Across 156 configurations on Persian medical board questions, Chain-of-Thought prompting raised accuracy while increasing overconfidence, and emotional prompting inflated confidence without accuracy gains.