Disagreement resolution achieves 62.1% accuracy for non-expert models in identifying truth, outperforming standard debate at 49.2% by shifting from adversarial persuasion to collaborative consensus-building.
org/CorpusID:265551974
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CY 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Collaborative Disagreement Resolution for Scalable Oversight
Disagreement resolution achieves 62.1% accuracy for non-expert models in identifying truth, outperforming standard debate at 49.2% by shifting from adversarial persuasion to collaborative consensus-building.