An adaptive test-time scaling method that selects reasoning strategies based on synthetically generated similar questions improves ROUGE-L on seven CQA benchmarks while claiming lower token use.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
T$^2$: An Adaptive Test-Time Scaling Strategy for Contextual Question Answering
An adaptive test-time scaling method that selects reasoning strategies based on synthetically generated similar questions improves ROUGE-L on seven CQA benchmarks while claiming lower token use.