Image de couverture de livre

Sample Efficient Preference Alignment in LLMs via Active Exploration

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Mehta, Viraj, Belakaria, Syrine, Das, Vikramjeet, Neopane, Ojash, Dai, Yijia, Bogunovic, Ilija, Engelhardt, Barbara, Ermon, Stefano, Schneider, Jeff, Neiswanger, Willie
Format:	Preprint
Publié:	2023
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Sharpe Ratio-Guided Active Learning for Preference Optimization in RLHF
par: Belakaria, Syrine, et autres
Publié: (2025)

Preference-Guided Diffusion for Multi-Objective Offline Optimization
par: Annadani, Yashas, et autres
Publié: (2025)

Active Learning for Derivative-Based Global Sensitivity Analysis with Gaussian Processes
par: Belakaria, Syrine, et autres
Publié: (2024)

Non-Myopic Multi-Objective Bayesian Optimization
par: Belakaria, Syrine, et autres
Publié: (2024)

Optimistic Algorithms for Adaptive Estimation of the Average Treatment Effect
par: Neopane, Ojash, et autres
Publié: (2025)

Logarithmic Neyman Regret for Adaptive Estimation of the Average Treatment Effect
par: Neopane, Ojash, et autres
Publié: (2024)

Probabilistic Graphical Models: A Concise Tutorial
par: Maasch, Jacqueline, et autres
Publié: (2025)

Uncertainty Quantification for Forward and Inverse Problems of PDEs via Latent Global Evolution
par: Wu, Tailin, et autres
Publié: (2024)

Group Robust Preference Optimization in Reward-free RLHF
par: Ramesh, Shyam Sundhar, et autres
Publié: (2024)

Pareto Front-Diverse Batch Multi-Objective Bayesian Optimization
par: Ahmadianshalchi, Alaleh, et autres
Publié: (2024)

Sample-efficient Bayesian Optimisation Using Known Invariances
par: Brown, Theodore, et autres
Publié: (2024)

This Is Your Doge, If It Please You: Exploring Deception and Robustness in Mixture of LLMs
par: Wolf, Lorenz, et autres
Publié: (2025)

Right Now, Wrong Then: Non-Stationary Direct Preference Optimization under Preference Drift
par: Son, Seongho, et autres
Publié: (2024)

Neural Nonmyopic Bayesian Optimization in Dynamic Cost Settings
par: Truong, Sang T., et autres
Publié: (2026)

Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data
par: Tajwar, Fahim, et autres
Publié: (2024)

Beyond Pairwise Preferences: Listwise Reward-Aware Alignment for Diffusion Models
par: Wang, Austin, et autres
Publié: (2026)

Robust Bayesian Optimisation with Unbounded Corruptions
par: Ezzerg, Abdelhamid, et autres
Publié: (2025)

Overton Pluralistic Reinforcement Learning for Large Language Models
par: Fu, Yu, et autres
Publié: (2026)

Euclid: Supercharging Multimodal LLMs with Synthetic High-Fidelity Visual Descriptions
par: Zhang, Jiarui, et autres
Publié: (2024)

Divergence Minimization Preference Optimization for Diffusion Model Alignment
par: Li, Binxu, et autres
Publié: (2025)

Efficient Evaluation of Multi-Task Robot Policies With Active Experiment Selection
par: Anwar, Abrar, et autres
Publié: (2025)

RSPO: Regularized Self-Play Alignment of Large Language Models
par: Tang, Xiaohang, et autres
Publié: (2025)

DeLLMa: Decision Making Under Uncertainty with Large Language Models
par: Liu, Ollie, et autres
Publié: (2024)

Reviving Any-Subset Autoregressive Models with Principled Parallel Sampling and Speculative Decoding
par: Guo, Gabe, et autres
Publié: (2025)

wd1: Weighted Policy Optimization for Reasoning in Diffusion Language Models
par: Tang, Xiaohang, et autres
Publié: (2025)

REDUCR: Robust Data Downsampling Using Class Priority Reweighting
par: Bankes, William, et autres
Publié: (2023)

Adversarially Robust Decision Transformer
par: Tang, Xiaohang, et autres
Publié: (2024)

Mean-Field Bayesian Optimisation
par: Steinberg, Petar, et autres
Publié: (2025)

Synthetic Data is Sufficient for Zero-Shot Visual Generalization from Offline Data
par: Güzel, Ahmet H., et autres
Publié: (2025)

On Almost Surely Safe Alignment of Large Language Models at Inference-Time
par: Ji, Xiaotong, et autres
Publié: (2025)

Sample-Efficient Regret-Minimizing Double Oracle in Extensive-Form Games
par: Tang, Xiaohang, et autres
Publié: (2024)

METAGENE-1: Metagenomic Foundation Model for Pandemic Monitoring
par: Liu, Ollie, et autres
Publié: (2025)

Rethinking RL for LLM Reasoning: It's Sparse Policy Selection, Not Capability Learning
par: Akgül, Ömer Faruk, et autres
Publié: (2026)

ActiveDPO: Active Direct Preference Optimization for Sample-Efficient Alignment
par: Lin, Xiaoqiang, et autres
Publié: (2025)

LLM-WikiRace Benchmark: How Far Can LLMs Plan over Real-World Knowledge Graphs?
par: Ziomek, Juliusz, et autres
Publié: (2026)

Disentangling Length from Quality in Direct Preference Optimization
par: Park, Ryan, et autres
Publié: (2024)

LLM Unlearning Without an Expert Curated Dataset
par: Zhu, Xiaoyuan, et autres
Publié: (2025)

Supercharging Simulation-Based Inference for Bayesian Optimal Experimental Design
par: Klein, Samuel, et autres
Publié: (2026)

From Calibration to Collaboration: LLM Uncertainty Quantification Should Be More Human-Centered
par: Devic, Siddartha, et autres
Publié: (2025)

Active Preference Optimization for Sample Efficient RLHF
par: Das, Nirjhar, et autres
Publié: (2024)