Oracle per-example routing among decoding, voting, and debate yields +13-14 pp gains over the best fixed protocol, but vote-entropy thresholds and learned routers recover only 1-2 pp with non-significant results.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Statistical Scouting Finds Debate-Safe but Not Debate-Useful Cases: A Matched-Ceiling Study of Open-Weight LLM Reasoning Protocols
Oracle per-example routing among decoding, voting, and debate yields +13-14 pp gains over the best fixed protocol, but vote-entropy thresholds and learned routers recover only 1-2 pp with non-significant results.