Prefix consistency weights CoT answers by their regeneration frequency from truncated prefixes and reaches standard self-consistency accuracy at a median 4.6x fewer tokens across five models and four benchmarks.
Substituting the above probabilities, we obtain Φw(a) =w(1)π(a)T(a→a) +w( 1 2) π(a) +π →(a)−2π(a)T(a→a)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Reliable Chain-of-Thought via Prefix Consistency
Prefix consistency weights CoT answers by their regeneration frequency from truncated prefixes and reaches standard self-consistency accuracy at a median 4.6x fewer tokens across five models and four benchmarks.