Alignment by Confident Debate: Preference Learning from Multi-Agent Debate
cs.AI
Submitted: 2026-11-06
Updated: 2026-11-06
Terminology
Sources
- Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs
- Program Synthesis with Large Language Models
- Constitutional AI: Harmlessness from AI Feedback
- Universal Self-Consistency for Large Language Model Generation
- Training Verifiers to Solve Math Word Problems
- Improving Factuality and Reasoning in Language Models through Multiagent Debate
- The Llama 3 Herd of Models
- Reinforced Self-Training (ReST) for Language Modeling
- AI safety via debate
- Language Models (Mostly) Know What They Know
- Enhancing Multi-Agent Debate System Performance via Confidence Expression
- MALT: Improving Reasoning with Multi-Agent LLM Training
- Epistemic Gain, Aleatoric Cost: Uncertainty Decomposition in Multi-Agent Debate for Math Reasoning
- Qwen2.5 Technical Report
- Self-Improvement of Language Models by Post-Training on Multi-Agent Debate
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Gemma 3 Technical Report
- Self-Consistency Improves Chain of Thought Reasoning in Language Models
- Self-Rewarding Language Models
- Scaling Relationship on Learning Mathematical Reasoning with Large Language Models
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