Retrieving few-shot examples by computational-graph similarity improves LLM math word problem accuracy by up to 6.7 points over semantic retrieval, without retraining the generator.
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
-
Learning by Analogy: Enhancing Few-Shot Prompting for Math Word Problem Solving with Computational Graph-Based Retrieval
Retrieving few-shot examples by computational-graph similarity improves LLM math word problem accuracy by up to 6.7 points over semantic retrieval, without retraining the generator.