conftrace_

best-of-n sampling

15 papers

Explore in graph

Also known as

BON

Co-occurring keywords

large language model (13587) inference-time alignment (16) test-time scaling (85) language model alignment (142) beam search (309) process reward model (53) reward model (276) tree search (86) model alignment (226) mathematical reasoning (407)

Papers

Inference-Aware Prompt Optimization for Aligning Black-Box Large Language Models AAAI 2026
Jailbreaks as Inference-Time Alignment: A Framework for Understanding Safety Failures in LLMs EACL 2026
Think Hard Only When Needed: A Hybrid Best-of-N and Beam Search for Efficient Test-Time Compute EACL 2026
From Mathematical Reasoning to Code: Generalization of Process Reward Models in Test-Time Scaling AAAI 2026
Test-time Diverse Reasoning by Riemannian Activation Steering AAAI 2026
Regularized Best-of-N Sampling with Minimum Bayes Risk Objective for Language Model Alignment NAACL 2025
Reward-Guided Tree Search for Inference Time Alignment of Large Language Models NAACL 2025
Speculative Decoding for Multi-Sample Inference EMNLP 2025
UvA-MT’s Participation in the WMT25 General Translation Shared Task EMNLP 2025
TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling EMNLP 2025
AgentRM: Enhancing Agent Generalization with Reward Modeling ACL 2025
BoN Appetit Team at LeWiDi-2025: Best-of-N Test-time Scaling Can Not Stomach Annotation Disagreements (Yet) EMNLP 2025
VL-RewardBench: A Challenging Benchmark for Vision-Language Generative Reward Models CVPR 2025
Scaling LLM Inference Efficiently with Optimized Sample Compute Allocation NAACL 2025
BoNBoN Alignment for Large Language Models and the Sweetness of Best-of-n Sampling NIPS 2024