Efficient Best-Of-N with Radial Consensus Score
cs.CL
Submitted: 2026-04-14
Updated: 2026-10-21
Terminology
Sources
- Universal Self-Consistency for Large Language Model Generation
- ModeX: Evaluator-Free Best-of-N Selection for Open-Ended Generation
- Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?
- Training Verifiers to Solve Math Word Problems
- Certified Self-Consistency: Statistical Guarantees and Test-Time Training for Reliable Reasoning in LLMs
- The Llama 3 Herd of Models
- Aligning AI With Shared Human Values
- Scalable Best-of-N Selection for Large Language Models via Self-Certainty
- Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models
- Distance Is All You Need: Radial Dispersion for Uncertainty Estimation in Large Language Models
- Hear Both Sides: Efficient Multi-Agent Debate via Diversity-Aware Message Retention
- Geometric Uncertainty for Detecting and Correcting Hallucinations in LLMs
- Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
- Gemma 2: Improving Open Language Models at a Practical Size
- Self-Consistency Improves Chain of Thought Reasoning in Language Models
- Crowdsourcing Multiple Choice Science Questions
- Qwen3 Technical Report
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering