Multi-agent debate in medical QA creates a consistency illusion by reducing answer contradictions while decreasing reasoning similarity; the Grounded Debate Protocol improves alignment with large effect sizes.
Building Efficient Universal Classifiers with Natural Language Inference; 2023
5 Pith papers cite this work, alongside 11 external citations. Polarity classification is still indexing.
5
Pith papers citing it
11
external citations · external index
years
2026 5verdicts
UNVERDICTED 5representative citing papers
Credence replaces Jaccard-F1 with Semantic-F1 for claim decomposition quality and proves convergence properties for rule-based and LLM-based repair under stated assumptions, reporting +15-32pp gains on three domain benchmarks.
Fairness mitigation in personalized text generation is objective-dependent with methods occupying different regions of the fairness-personalization Pareto frontier rather than any single strategy dominating all objectives.
Decomposing annotation tasks using centers from centering theory reduces aggregate inferential load via a degrees-of-freedom model and enables better sub-task allocation.
Ideological discrepancy between publishers and news content on Facebook is associated with nonlinear declines in audience consensus at extremes of alignment and mismatch, plus higher toxicity under mismatch, during a Brazilian election.
citing papers explorer
-
The Consistency Illusion: How Multi-Agent Debate Hides Reasoning Misalignment
Multi-agent debate in medical QA creates a consistency illusion by reducing answer contradictions while decreasing reasoning similarity; the Grounded Debate Protocol improves alignment with large effect sizes.
-
CREDENCE: Claim Reduction for Decomposition & Enhanced Credibility -- Semantic Metrics and Convergence Analysis
Credence replaces Jaccard-F1 with Semantic-F1 for claim decomposition quality and proves convergence properties for rule-based and LLM-based repair under stated assumptions, reporting +15-32pp gains on three domain benchmarks.
-
Pareto-Guided Teacher Alignment for Fair Personalized Text Generation
Fairness mitigation in personalized text generation is objective-dependent with methods occupying different regions of the fairness-personalization Pareto frontier rather than any single strategy dominating all objectives.
-
Task Decomposition for Efficient Annotation
Decomposing annotation tasks using centers from centering theory reduces aggregate inferential load via a degrees-of-freedom model and enables better sub-task allocation.
-
Ideological discrepancy between publishers and news content is linked with audience engagement and consensus on Facebook
Ideological discrepancy between publishers and news content on Facebook is associated with nonlinear declines in audience consensus at extremes of alignment and mismatch, plus higher toxicity under mismatch, during a Brazilian election.