Image de couverture de livre

Adversarial Training of Reward Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Bukharin, Alexander, Qian, Haifeng, Sun, Shengyang, Renduchintala, Adithya, Singhal, Soumye, Wang, Zhilin, Kuchaiev, Oleksii, Delalleau, Olivier, Zhao, Tuo
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Reward-aware Preference Optimization: A Unified Mathematical Framework for Model Alignment
par: Sun, Shengyang, et autres
Publié: (2025)

Tied-Lora: Enhancing parameter efficiency of LoRA with weight tying
par: Renduchintala, Adithya, et autres
Publié: (2023)

HelpSteer2-Preference: Complementing Ratings with Preferences
par: Wang, Zhilin, et autres
Publié: (2024)

HelpSteer3-Preference: Open Human-Annotated Preference Data across Diverse Tasks and Languages
par: Wang, Zhilin, et autres
Publié: (2025)

RLBFF: Binary Flexible Feedback to bridge between Human Feedback & Verifiable Rewards
par: Wang, Zhilin, et autres
Publié: (2025)

NeMo-Aligner: Scalable Toolkit for Efficient Model Alignment
par: Shen, Gerald, et autres
Publié: (2024)

HelpSteer3: Human-Annotated Feedback and Edit Data to Empower Inference-Time Scaling in Open-Ended General-Domain Tasks
par: Wang, Zhilin, et autres
Publié: (2025)

HelpSteer2: Open-source dataset for training top-performing reward models
par: Wang, Zhilin, et autres
Publié: (2024)

Deep Reinforcement Learning from Hierarchical Preference Design
par: Bukharin, Alexander, et autres
Publié: (2023)

Think Twice: Branch-and-Rethink Reasoning Reward Model
par: Jiao, Yizhu, et autres
Publié: (2025)

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

Adversarial Training for Process Reward Models
par: Juneja, Gurusha, et autres
Publié: (2025)

Robust Reinforcement Learning from Corrupted Human Feedback
par: Bukharin, Alexander, et autres
Publié: (2024)

Adaptive Preference Scaling for Reinforcement Learning with Human Feedback
par: Hong, Ilgee, et autres
Publié: (2024)

Data Diversity Matters for Robust Instruction Tuning
par: Bukharin, Alexander, et autres
Publié: (2023)

Democratic Training Against Universal Adversarial Perturbations
par: Sun, Bing, et autres
Publié: (2025)

DISPROTBENCH: Uncovering the Functional Limits of Protein Structure Prediction Models in Intrinsically Disordered Regions
par: Zeng, Xinyue, et autres
Publié: (2025)

Contrastive Adversarial Training for Unsupervised Domain Adaptation
par: Chen, Jiahong, et autres
Publié: (2024)

Learning Personalized Ad Impact via Contextual Reinforcement Learning under Delayed Rewards
par: Cheng, Yuwei, et autres
Publié: (2025)

Semi-Supervised Reward Modeling via Iterative Self-Training
par: He, Yifei, et autres
Publié: (2024)

Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training
par: Liu, Mingjie, et autres
Publié: (2025)

IQL-TD-MPC: Implicit Q-Learning for Hierarchical Model Predictive Control
par: Chitnis, Rohan, et autres
Publié: (2023)

Heterogeneity in Formal Linguistic Competence of Language Models: Is Data the Real Bottleneck?
par: Renduchintala, H S V N S Kowndinya, et autres
Publié: (2026)

Diffusion-Reward Adversarial Imitation Learning
par: Lai, Chun-Mao, et autres
Publié: (2024)

Revealing the Challenges of Sim-to-Real Transfer in Model-Based Reinforcement Learning via Latent Space Modeling
par: Lin, Zhilin, et autres
Publié: (2025)

Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking
par: Laidlaw, Cassidy, et autres
Publié: (2024)

DiagnoLLM: A Hybrid Bayesian Neural Language Framework for Interpretable Disease Diagnosis
par: Xu, Bowen, et autres
Publié: (2025)

Adversarial Reward Auditing for Active Detection and Mitigation of Reward Hacking
par: Beigi, Mohammad, et autres
Publié: (2026)

GENUINE: Graph Enhanced Multi-level Uncertainty Estimation for Large Language Models
par: Wang, Tuo, et autres
Publié: (2025)

Probabilistic Uncertain Reward Model
par: Sun, Wangtao, et autres
Publié: (2025)

Think-RM: Enabling Long-Horizon Reasoning in Generative Reward Models
par: Hong, Ilgee, et autres
Publié: (2025)

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning
par: Li, Mengqi, et autres
Publié: (2025)

Benchmarking Deep Learning Models for Raman Spectroscopy Across Open-Source Datasets
par: Sineesh, Adithya, et autres
Publié: (2026)

Approximation of Log-Partition Function in Policy Mirror Descent Induces Implicit Regularization for LLM Post-Training
par: Xu, Zhenghao, et autres
Publié: (2026)

Generative Adversarial Post-Training Mitigates Reward Hacking in Live Human-AI Music Interaction
par: Wu, Yusong, et autres
Publié: (2025)

Non-exchangeable Conformal Prediction for Temporal Graph Neural Networks
par: Wang, Tuo, et autres
Publié: (2025)

Adversarial Training: A Survey
par: Zhao, Mengnan, et autres
Publié: (2024)

Provably Efficient Online RLHF with One-Pass Reward Modeling
par: Li, Long-Fei, et autres
Publié: (2025)

SparseSSM: Efficient Selective Structured State Space Models Can Be Pruned in One-Shot
par: Tuo, Kaiwen, et autres
Publié: (2025)

Ask a Strong LLM Judge when Your Reward Model is Uncertain
par: Xu, Zhenghao, et autres
Publié: (2025)