Rational Alignments of Superintelligences via Debates
cs.AI
Submitted: 2026-11-12
Updated: 2026-11-12
Terminology
Sources
- Debate is efficient with your time
- Avoiding Obfuscation with Prover-Estimator Debate
- AI safety via debate
- (When) Is Truth-telling Favored in AI Debate?
- The Road to Artificial SuperIntelligence: A Comprehensive Survey of Superalignment
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents