On a new 15,000-item proportional analogy MCQ benchmark, GPT-3.5-Turbo reaches 55.25% accuracy, and prompts that inject the target semantic relation outperform exemplar and structured-knowledge prompts.
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
-
KnowledgePrompts: Exploring the Abilities of Large Language Models to Solve Proportional Analogies via Knowledge-Enhanced Prompting
On a new 15,000-item proportional analogy MCQ benchmark, GPT-3.5-Turbo reaches 55.25% accuracy, and prompts that inject the target semantic relation outperform exemplar and structured-knowledge prompts.