Proposes RAP, a retrieval-based approximate prior method, to predict performance of symbolic programs and LLM prompts on new tasks using a Bernoulli model and corpus-derived performance distributions.
How predictable are large language model capabilities? a case study on big-bench
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Predicting Performance of Symbolic and Prompt Programs with Examples
Proposes RAP, a retrieval-based approximate prior method, to predict performance of symbolic programs and LLM prompts on new tasks using a Bernoulli model and corpus-derived performance distributions.