Imagen de Portada

Counterfactual Reward Model Training for Bias Mitigation in Multimodal Reinforcement Learning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Mathew, Sheryl, Harshit, N
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF
por: Zhao, Kangwen, et al.
Publicado: (2025)

Relative Counterfactual Contrastive Learning for Mitigating Pretrained Stance Bias in Stance Detection
por: Zhang, Jiarui, et al.
Publicado: (2024)

Directional Alignment Mitigates Reward Hacking in Reinforcement Learning for Language Models
por: Deng, Wenlong, et al.
Publicado: (2026)

Diagnosing and Mitigating System Bias in Self-Rewarding RL
por: Tan, Chuyi, et al.
Publicado: (2025)

Mitigating Gender Bias in Depression Detection via Counterfactual Inference
por: Hu, Mingxuan, et al.
Publicado: (2025)

Counterfactually Safe Reinforcement Learning
por: Li, Jingyi, et al.
Publicado: (2026)

Explaining Learned Reward Functions with Counterfactual Trajectories
por: Wehner, Jan, et al.
Publicado: (2024)

Tabular and Deep Reinforcement Learning for Gittins Index
por: Dhankhar, Harshit, et al.
Publicado: (2024)

Maximum Entropy Reinforcement Learning with Diffusion Policy
por: Dong, Xiaoyi, et al.
Publicado: (2025)

Towards the Mitigation of Confirmation Bias in Semi-supervised Learning: a Debiased Training Perspective
por: Wang, Yu, et al.
Publicado: (2024)

Training Data Efficiency in Multimodal Process Reward Models
por: Li, Jinyuan, et al.
Publicado: (2026)

AGR: Age Group fairness Reward for Bias Mitigation in LLMs
por: Cao, Shuirong, et al.
Publicado: (2024)

Grounding by Trying: LLMs with Reinforcement Learning-Enhanced Retrieval
por: Hsu, Sheryl, et al.
Publicado: (2024)

Certifying Counterfactual Bias in LLMs
por: Chaudhary, Isha, et al.
Publicado: (2024)

Reward-Conditioned Reinforcement Learning
por: Nauman, Michal, et al.
Publicado: (2026)

Fisher-Guided Selective Forgetting: Mitigating The Primacy Bias in Deep Reinforcement Learning
por: Falzari, Massimiliano, et al.
Publicado: (2025)

Deep Reinforcement Learning with Hybrid Intrinsic Reward Model
por: Yuan, Mingqi, et al.
Publicado: (2025)

Beyond Simple Sum of Delayed Rewards: Non-Markovian Reward Modeling for Reinforcement Learning
por: Tang, Yuting, et al.
Publicado: (2024)

IR$^3$: Contrastive Inverse Reinforcement Learning for Interpretable Detection and Mitigation of Reward Hacking
por: Beigi, Mohammad, et al.
Publicado: (2026)

Reward Model Ensembles Help Mitigate Overoptimization
por: Coste, Thomas, et al.
Publicado: (2023)

Evaluating the Impact of Pulse Oximetry Bias in Machine Learning under Counterfactual Thinking
por: Martins, Inês, et al.
Publicado: (2024)

Alternating Reinforcement Learning for Rubric-Based Reward Modeling in Non-Verifiable LLM Post-Training
por: Xu, Ran, et al.
Publicado: (2026)

Entropy-Guided Data-Efficient Training for Multimodal Reasoning Reward Models
por: Yang, Shidong, et al.
Publicado: (2026)

They're All Doctors: Synthesizing Diverse Counterfactuals to Mitigate Associative Bias
por: Magid, Salma Abdel, et al.
Publicado: (2024)

JacQuant: STE-Free Quantization-Aware Training via Learned Jacobian Surrogates
por: Yi, Kai, et al.
Publicado: (2026)

Information-Theoretic Reward Modeling for Stable RLHF: Detecting and Mitigating Reward Hacking
por: Miao, Yuchun, et al.
Publicado: (2025)

Helping or Herding? Reward Model Ensembles Mitigate but do not Eliminate Reward Hacking
por: Eisenstein, Jacob, et al.
Publicado: (2023)

Adversarial Training of Reward Models
por: Bukharin, Alexander, et al.
Publicado: (2025)

Goal-Driven Reward by Video Diffusion Models for Reinforcement Learning
por: Wang, Qi, et al.
Publicado: (2025)

DCAST: Diverse Class-Aware Self-Training Mitigates Selection Bias for Fairer Learning
por: Tepeli, Yasin I., et al.
Publicado: (2024)

ELO-Rated Sequence Rewards: Advancing Reinforcement Learning Models
por: Ju, Qi, et al.
Publicado: (2024)

Reward Design for Reinforcement Learning Agents
por: Devidze, Rati
Publicado: (2025)

Counterfactual Fairness through Transforming Data Orthogonal to Bias
por: Chen, Shuyi, et al.
Publicado: (2024)

Reinforcement Learning from Bagged Reward
por: Tang, Yuting, et al.
Publicado: (2024)

The Value of Reward Lookahead in Reinforcement Learning
por: Merlis, Nadav, et al.
Publicado: (2024)

Informativeness of Reward Functions in Reinforcement Learning
por: Devidze, Rati, et al.
Publicado: (2024)

To the Max: Reinventing Reward in Reinforcement Learning
por: Veviurko, Grigorii, et al.
Publicado: (2024)

The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward
por: Li, Long, et al.
Publicado: (2025)

IRIS: Implicit Reward-Guided Internal Sifting for Mitigating Multimodal Hallucination
por: Li, Yuanshuai, et al.
Publicado: (2026)

Towards Better Alignment: Training Diffusion Models with Reinforcement Learning Against Sparse Rewards
por: Hu, Zijing, et al.
Publicado: (2025)