Image de couverture de livre

Learning Generative Selection for Best-of-N

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Toshniwal, Shubham, Ficek, Aleksander, Jain, Siddhartha, Du, Wei, Noroozi, Vahid, Mahdavi, Sadegh, Majumdar, Somshubra, Gitman, Igor
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Scoring Verifiers: Evaluating Synthetic Verification for Code and Reasoning
par: Ficek, Aleksander, et autres
Publié: (2025)

GenSelect: A Generative Approach to Best-of-N
par: Toshniwal, Shubham, et autres
Publié: (2025)

Scaling Test-Time Compute to Achieve IOI Gold Medal with Open-Weight Models
par: Samadi, Mehrzad, et autres
Publié: (2025)

OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset
par: Toshniwal, Shubham, et autres
Publié: (2024)

OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data
par: Toshniwal, Shubham, et autres
Publié: (2024)

Instruction Data Generation and Unsupervised Adaptation for Speech Language Models
par: Noroozi, Vahid, et autres
Publié: (2024)

Scaling Generative Verifiers For Natural Language Mathematical Proof Verification And Selection
par: Mahdavi, Sadegh, et autres
Publié: (2025)

AIMO-2 Winning Solution: Building State-of-the-Art Mathematical Reasoning Models with OpenMathReasoning dataset
par: Moshkov, Ivan, et autres
Publié: (2025)

OpenCodeReasoning: Advancing Data Distillation for Competitive Coding
par: Ahmad, Wasi Uddin, et autres
Publié: (2025)

OpenCodeReasoning-II: A Simple Test Time Scaling Approach via Self-Critique
par: Ahmad, Wasi Uddin, et autres
Publié: (2025)

Genetic Instruct: Scaling up Synthetic Generation of Coding Instructions for Large Language Models
par: Majumdar, Somshubra, et autres
Publié: (2024)

Nemotron-Math: Efficient Long-Context Distillation of Mathematical Reasoning from Multi-Mode Supervision
par: Du, Wei, et autres
Publié: (2025)

OpenCodeInstruct: A Large-scale Instruction Tuning Dataset for Code LLMs
par: Ahmad, Wasi Uddin, et autres
Publié: (2025)

GPT vs RETRO: Exploring the Intersection of Retrieval and Parameter-Efficient Fine-Tuning
par: Ficek, Aleksander, et autres
Publié: (2024)

IdentifyMe: A Challenging Long-Context Mention Resolution Benchmark for LLMs
par: Manikantan, Kawshik, et autres
Publié: (2024)

Major Entity Identification: A Generalizable Alternative to Coreference Resolution
par: Manikantan, Kawshik, et autres
Publié: (2024)

Code Pretraining Improves Entity Tracking Abilities of Language Models
par: Kim, Najoung, et autres
Publié: (2024)

Leveraging Online Olympiad-Level Math Problems for LLMs Training and Contamination-Resistant Evaluation
par: Mahdavi, Sadegh, et autres
Publié: (2025)

Inferring from Logits: Exploring Best Practices for Decoding-Free Generative Candidate Selection
par: Ma, Mingyu Derek, et autres
Publié: (2025)

Scalable Best-of-N Selection for Large Language Models via Self-Certainty
par: Kang, Zhewei, et autres
Publié: (2025)

Best-of-N Jailbreaking
par: Hughes, John, et autres
Publié: (2024)

Stateful Conformer with Cache-based Inference for Streaming Automatic Speech Recognition
par: Noroozi, Vahid, et autres
Publié: (2023)

Variational Best-of-N Alignment
par: Amini, Afra, et autres
Publié: (2024)

Lightweight reranking for language model generations
par: Jain, Siddhartha, et autres
Publié: (2023)

Majority of the Bests: Improving Best-of-N via Bootstrapping
par: Rakhsha, Amin, et autres
Publié: (2025)

AdaBoN: Adaptive Best-of-N Alignment
par: Raman, Vinod, et autres
Publié: (2025)

NeMo-Inspector: A Visualization Tool for LLM Generation Analysis
par: Gitman, Daria, et autres
Publié: (2025)

BOND: Aligning LLMs with Best-of-N Distillation
par: Sessa, Pier Giuseppe, et autres
Publié: (2024)

Advantage Shaping as Surrogate Reward Maximization: Unifying Pass@K Policy Gradients
par: Thrampoulidis, Christos, et autres
Publié: (2025)

Regret-Free Reinforcement Learning for LTL Specifications
par: Majumdar, Rupak, et autres
Publié: (2024)

The Strongest Teacher Is Not Always the Best Teacher: Student-Centric Answer Selection
par: Hu, Zhengyu, et autres
Publié: (2026)

ModeX: Evaluator-Free Best-of-N Selection for Open-Ended Generation
par: Choi, Hyeong Kyu, et autres
Publié: (2026)

Training Domain Draft Models for Speculative Decoding: Best Practices and Insights
par: Hong, Fenglu, et autres
Publié: (2025)

Comparative Analysis of Demonstration Selection Algorithms for LLM In-Context Learning
par: Shu, Dong, et autres
Publié: (2024)

TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling
par: Qiu, Jiahao, et autres
Publié: (2024)

SmallToLarge (S2L): Scalable Data Selection for Fine-tuning Large Language Models by Summarizing Training Trajectories of Small Models
par: Yang, Yu, et autres
Publié: (2024)

Nemotron-4 340B Technical Report
par: Nvidia, et autres
Publié: (2024)

Inference-Aware Fine-Tuning for Best-of-N Sampling in Large Language Models
par: Chow, Yinlam, et autres
Publié: (2024)

When LLM Judge Scores Look Good but Best-of-N Decisions Fail
par: Landesberg, Eddie
Publié: (2026)

Mining Intrinsic Rewards from LLM Hidden States for Efficient Best-of-N Sampling
par: Guo, Jizhou, et autres
Publié: (2025)