conftrace_

best-of-n selection

5 papers

Explore in graph

Also known as

BON

Co-occurring keywords · papers mentioning both

large language model (2) inference-time scaling (2) majority voting (2) process-supervised reward model (1) step-level verification (1) prompt diversity (1) sampling optimization (1) diversity fidelity tradeoff (1) step-level reward signal (1) sampling diversity (1)

Papers

ModeX: Evaluator-Free Best-of-N Selection for Open-Ended Generation ACL 2026 On the Effect of Sampling Diversity in Scaling LLM Inference UAI 2026 OptScale: Probabilistic Optimality for Inference-time Scaling AAAI 2026 AdaRewriter: Unleashing the Power of Prompting-based Conversational Query Reformulation via Test-Time Adaptation EMNLP 2025 Process-Supervised Reward Models for Verifying Clinical Note Generation: A Scalable Approach Guided by Domain Expertise EMNLP 2025