Claim record · edition 1.0.0
si-007Active research
Allocating additional computation at inference time can, in studied settings, improve results more than spending the equivalent compute on additional parameters.
This trade-off is the basis of reasoning-style systems and is reported with verifier-based and search-based methods.
Limits of this claim
Demonstrated within specific task families and compute budgets. It is not established as a general substitution, and the studied regimes do not license extrapolation.
Supporting source records · 2
primary paperContent verified
Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
Snell et al. · 2024
The inference-time compute trade-off against parameter scaling.
Source record →primary paperContent verified
Training Verifiers to Solve Math Word Problems
Cobbe et al. · 2021
Verifier-based selection over sampled solutions, an early inference-time compute method.
Source record →