Sudoku
A Sudoku reasoning task, commonly used as a benchmark for evaluating the reasoning ability of language models and diffusion models.
Timeline (last 90 days)
On the Sudoku task, Brownian corruption and moment-matched vMF corruption give nearly identical results across four samplers and five budgets.
The gain from the sampler can be decomposed into a memory effect (present on both Sudoku and GSM8K) and a token-selection effect (present on GSM8K and most pronounced at small budgets).
The researchers validated the effectiveness of the hierarchical verification framework using structured world modeling tasks such as Maze and Sudoku.
All Facts (3)
On the Sudoku task, Brownian corruption and moment-matched vMF corruption give nearly identical results across four samplers and five budgets.
50%UnverifiedThe gain from the sampler can be decomposed into a memory effect (present on both Sudoku and GSM8K) and a token-selection effect (present on GSM8K and most pronounced at small budgets).
50%UnverifiedThe researchers validated the effectiveness of the hierarchical verification framework using structured world modeling tasks such as Maze and Sudoku.
50%