Image de couverture de livre

Adversarial Reward Auditing for Active Detection and Mitigation of Reward Hacking

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Beigi, Mohammad, Jin, Ming, Zhang, Junshan, Wang, Qifan, Huang, Lifu
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

IR$^3$: Contrastive Inverse Reinforcement Learning for Interpretable Detection and Mitigation of Reward Hacking
par: Beigi, Mohammad, et autres
Publié: (2026)

Reward Shaping to Mitigate Reward Hacking in RLHF
par: Fu, Jiayi, et autres
Publié: (2025)

Reward Hacking Mitigation using Verifiable Composite Rewards
par: Tarek, Mirza Farhan Bin, et autres
Publié: (2025)

Repairing Reward Functions with Feedback to Mitigate Reward Hacking
par: Hatgis-Kessell, Stephane, et autres
Publié: (2025)

ODIN: Disentangled Reward Mitigates Hacking in RLHF
par: Chen, Lichang, et autres
Publié: (2024)

InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling
par: Miao, Yuchun, et autres
Publié: (2024)

Uncertainty-Aware Reward Discounting for Mitigating Reward Hacking
par: Singha, Disha
Publié: (2026)

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment
par: Wang, Chaoqi, et autres
Publié: (2025)

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

Hack-Verifiable Environments: Towards Evaluating Reward Hacking at Scale
par: Roth, Amit, et autres
Publié: (2026)

Mitigating Reward Hacking in RLHF via Advantage Sign Robustness
par: Ono, Shinnosuke, et autres
Publié: (2026)

Temper and Tilt Lead to SLOP: Reward Hacking Mitigation with Inference-Time Alignment
par: Wang, Ye, et autres
Publié: (2026)

MONA: Myopic Optimization with Non-myopic Approval Can Mitigate Multi-step Reward Hacking
par: Farquhar, Sebastian, et autres
Publié: (2025)

LLMs Gaming Verifiers: RLVR can Lead to Reward Hacking
par: Helff, Lukas, et autres
Publié: (2026)

Benchmarking Reward Hack Detection in Code Environments via Contrastive Analysis
par: Deshpande, Darshan, et autres
Publié: (2026)

Reward Hacking Benchmark: Measuring Exploits in LLM Agents with Tool Use
par: Thaman, Kunvar
Publié: (2026)

Gradient Regularization Prevents Reward Hacking in Reinforcement Learning from Human Feedback and Verifiable Rewards
par: Ackermann, Johannes, et autres
Publié: (2026)

IRIS: Implicit Reward-Guided Internal Sifting for Mitigating Multimodal Hallucination
par: Li, Yuanshuai, et autres
Publié: (2026)

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

GARDO: Reinforcing Diffusion Models without Reward Hacking
par: He, Haoran, et autres
Publié: (2025)

Feedback Loops With Language Models Drive In-Context Reward Hacking
par: Pan, Alexander, et autres
Publié: (2024)

Sail into the Headwind: Alignment via Robust Rewards and Dynamic Labels against Reward Hacking
par: Rashidinejad, Paria, et autres
Publié: (2024)

Sycophancy Mitigation Through Reinforcement Learning with Uncertainty-Aware Adaptive Reasoning Trajectories
par: Beigi, Mohammad, et autres
Publié: (2025)

Honesty to Subterfuge: In-Context Reinforcement Learning Can Make Honest Models Reward Hack
par: McKee-Reid, Leo, et autres
Publié: (2024)

Countdown-Code: A Testbed for Studying The Emergence and Generalization of Reward Hacking in RLVR
par: Khalifa, Muhammad, et autres
Publié: (2026)

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

Policy Filtration for RLHF to Mitigate Noise in Reward Models
par: Zhang, Chuheng, et autres
Publié: (2024)

Information-Theoretic Reward Modeling for Stable RLHF: Detecting and Mitigating Reward Hacking
par: Miao, Yuchun, et autres
Publié: (2025)

Learning Rewards, Not Labels: Adversarial Inverse Reinforcement Learning for Machinery Fault Detection
par: Neupane, Dhiraj, et autres
Publié: (2026)

Representation Without Reward: A JEPA Audit for LLM Fine-Tuning
par: Sengupta, Biswa
Publié: (2026)

SemiReward: A General Reward Model for Semi-supervised Learning
par: Li, Siyuan, et autres
Publié: (2023)

Overcoming Reward Overoptimization via Adversarial Policy Optimization with Lightweight Uncertainty Estimation
par: Zhang, Xiaoying, et autres
Publié: (2024)

Value of Information and Reward Specification in Active Inference and POMDPs
par: Wei, Ran
Publié: (2024)

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF
par: Zhao, Kangwen, et autres
Publié: (2025)

Mitigating Preference Hacking in Policy Optimization with Pessimism
par: Gupta, Dhawal, et autres
Publié: (2025)

Trust Region Reward Optimization and Proximal Inverse Reward Optimization Algorithm
par: Chen, Yang, et autres
Publié: (2025)

Debate as Reward: A Multi-Agent Reward System for Scientific Ideation via RL Post-Training
par: Salimi, Moein, et autres
Publié: (2026)

Efficient Process Reward Model Training via Active Learning
par: Duan, Keyu, et autres
Publié: (2025)

TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process Rewards
par: Xiong, Xiqiao, et autres
Publié: (2025)

Fine-tuning Language Models with Generative Adversarial Reward Modelling
par: Yu, Zhang Ze, et autres
Publié: (2023)