English
Related papers

Related papers: Fairness Aware Reward Optimization

200 papers

Although adversarial training (AT) has proven effective in enhancing the model's robustness, the recently revealed issue of fairness in robustness has not been well addressed, i.e. the robust accuracy varies significantly among different…

Computer Vision and Pattern Recognition · Computer Science 2024-03-29 Yanghao Zhang , Tianle Zhang , Ronghui Mu , Xiaowei Huang , Wenjie Ruan

Reinforcement learning (RL) systems typically optimize scalar reward functions that assume precise and reliable evaluation of outcomes. However, real-world objectives--especially those derived from human preferences--are often uncertain,…

Machine Learning · Computer Science 2026-04-30 Disha Singha

We study fairness in classification, where individuals are classified, e.g., admitted to a university, and the goal is to prevent discrimination against individuals based on their membership in some group, while maintaining utility for the…

Computational Complexity · Computer Science 2011-11-30 Cynthia Dwork , Moritz Hardt , Toniann Pitassi , Omer Reingold , Rich Zemel

Decision making in crucial applications such as lending, hiring, and college admissions has witnessed increasing use of algorithmic models and techniques as a result of a confluence of factors such as ubiquitous connectivity, ability to…

Artificial Intelligence · Computer Science 2020-09-08 G Roshan Lal , Sahin Cem Geyik , Krishnaram Kenthapadi

Multi-label classification (MLC) often suffers from performance disparities across labels. We propose \textbf{FairPO}, a framework combining preference-based loss and group-robust optimization to improve fairness by targeting…

Machine Learning · Computer Science 2025-12-01 Soumen Kumar Mondal , Prateek Chanda , Akshit Varmora , Ganesh Ramakrishnan

Many instances of algorithmic bias are caused by subpopulation shifts. For example, ML models often perform worse on demographic groups that are underrepresented in the training data. In this paper, we study whether enforcing algorithmic…

Machine Learning · Statistics 2021-10-28 Subha Maity , Debarghya Mukherjee , Mikhail Yurochkin , Yuekai Sun

Matrix-based optimizers have attracted growing interest for improving LLM training efficiency, with significant progress centered on orthogonalization/whitening based methods. While yielding substantial performance gains, a fundamental…

Machine Learning · Computer Science 2026-02-10 Wenbo Gong , Javier Zazo , Qijun Luo , Puqian Wang , James Hensman , Chao Ma

Large language models (LLMs) demonstrate impressive performance but lack the flexibility to adapt to human preferences quickly without retraining. In this work, we introduce Test-time Preference Optimization (TPO), a framework that aligns…

Computation and Language · Computer Science 2025-01-23 Yafu Li , Xuyang Hu , Xiaoye Qu , Linjie Li , Yu Cheng

Recent research has shown that seemingly fair machine learning models, when used to inform decisions that have an impact on peoples' lives or well-being (e.g., applications involving education, employment, and lending), can inadvertently…

Machine Learning · Computer Science 2022-08-26 Aline Weber , Blossom Metevier , Yuriy Brun , Philip S. Thomas , Bruno Castro da Silva

Machine Learning (ML) systems are increasingly used to support decision-making processes that affect individuals. However, these systems often rely on biased data, which can lead to unfair outcomes against specific groups. With the growing…

Machine Learning · Computer Science 2026-04-14 Joana Simões , João Correia

We initiate the study of fairness in reinforcement learning, where the actions of a learning algorithm may affect its environment and future rewards. Our fairness constraint requires that an algorithm never prefers one action over another…

Machine Learning · Computer Science 2017-08-08 Shahin Jabbari , Matthew Joseph , Michael Kearns , Jamie Morgenstern , Aaron Roth

Large Language Models (LLMs) can acquire extensive world knowledge through pre-training on large corpora. However, due to exposure to low-quality data, LLMs may exhibit harmful behavior without aligning with human values. The dominant…

Machine Learning · Computer Science 2023-10-11 Tianhao Wu , Banghua Zhu , Ruoyu Zhang , Zhaojin Wen , Kannan Ramchandran , Jiantao Jiao

Existing alignment methods directly use the reward model learned from user preference data to optimize an LLM policy, subject to KL regularization with respect to the base policy. This practice is suboptimal for maximizing user's utility…

Machine Learning · Computer Science 2026-02-04 Haichuan Wang , Tao Lin , Lingkai Kong , Ce Li , Hezi Jiang , Milind Tambe

Reward models (RMs) play a crucial role in Reinforcement Learning from Human Feedback by serving as proxies for human preferences in aligning large language models. However, they suffer from various biases which could lead to reward…

Artificial Intelligence · Computer Science 2026-03-18 Xiao Zhu , Chenmien Tan , Pinzhen Chen , Rico Sennrich , Huiming Wang , Yanlin Zhang , Hanxu Hu

Fairness in machine learning has attracted increasing attention in recent years. The fairness methods improving algorithmic fairness for in-distribution data may not perform well under distribution shifts. In this paper, we first…

Machine Learning · Computer Science 2023-10-24 Zhimeng Jiang , Xiaotian Han , Hongye Jin , Guanchu Wang , Rui Chen , Na Zou , Xia Hu

Fairness emerged as an important requirement to guarantee that Machine Learning (ML) predictive systems do not discriminate against specific individuals or entire sub-populations, in particular, minorities. Given the inherent subjectivity…

Machine Learning · Computer Science 2022-06-08 Karima Makhlouf , Sami Zhioua , Catuscia Palamidessi

Mathematical reasoning is a key benchmark for large language models. Reinforcement learning is a standard post-training mechanism for improving the reasoning capabilities of large language models, yet performance remains sensitive to the…

Computation and Language · Computer Science 2026-05-11 Arash Ahmadi , Sarah Sharif , Yaser , Banad

Offline imitation learning (offline IL) enables training effective policies without requiring explicit reward annotations. Recent approaches attempt to estimate rewards for unlabeled datasets using a small set of expert demonstrations.…

Machine Learning · Computer Science 2025-11-19 Shengjie Sun , Jiafei Lyu , Runze Liu , Mengbei Yan , Bo Liu , Deheng Ye , Xiu Li

Humans face countless scenarios that require reasoning and judgment in daily life. However, existing large language model training methods primarily allow models to learn from existing textual content or solve predetermined problems,…

Artificial Intelligence · Computer Science 2026-01-27 Yin Cai , Zhouhong Gu , Juntao Zhang , Ping Chen

Recently, there has been a rising awareness that when machine learning (ML) algorithms are used to automate choices, they may treat/affect individuals unfairly, with legal, ethical, or economic consequences. Recommender systems are…

Information Retrieval · Computer Science 2022-04-19 Mohammadmehdi Naghiaei , Hossein A. Rahmani , Yashar Deldjoo