English
Related papers

Related papers: Robust AI Evaluation through Maximal Lotteries

200 papers

A key challenge in training Large Language Models (LLMs) is properly aligning them with human preferences. Reinforcement Learning with Human Feedback (RLHF) uses pairwise comparisons from human annotators to train reward functions and has…

Machine Learning · Computer Science 2025-01-17 Ariel D. Procaccia , Benjamin Schiffer , Shirley Zhang

Learning from preference-based feedback has recently gained traction as a promising approach to align language models with human interests. While these aligned generative models have demonstrated impressive capabilities across various…

Machine Learning · Computer Science 2024-04-15 Sayak Ray Chowdhury , Anush Kini , Nagarajan Natarajan

In pruning, the Lottery Ticket Hypothesis posits that large networks contain sparse subnetworks, or winning tickets, that can be trained in isolation to match the performance of their dense counterparts. However, most existing approaches…

Artificial Intelligence · Computer Science 2026-01-30 Grzegorz Stefanski , Alberto Presta , Michal Byra

Reward models (RMs) are central to aligning large language models, yet their practical effectiveness hinges on generalization to unseen prompts and shifting distributions. Most existing RM evaluations rely on static, pre-annotated…

Computation and Language · Computer Science 2026-01-27 Shunyang Luo , Peibei Cao , Zhihui Zhu , Kehua Feng , Zhihua Wang , Keyan Ding

We study sequential decision making in environments where rewards are only partially observed, but can be modeled as a function of observed contexts and the chosen action by the decision maker. This setting, known as contextual bandits,…

Methodology · Statistics 2015-03-11 Miroslav Dudík , Dumitru Erhan , John Langford , Lihong Li

In social impact optimization, AI decision systems often rely on solvers that optimize well-calibrated mathematical objectives. However, these solvers cannot directly accommodate evolving human preferences, typically expressed in natural…

Artificial Intelligence · Computer Science 2025-09-23 Guojun Xiong , Milind Tambe

Reinforcement Learning from Human Feedback (RLHF) has emerged as a key technique for post-training large language models. Despite its empirical success, the theoretical understanding of RLHF is still limited, as learning the KL-regularized…

Machine Learning · Computer Science 2025-10-29 Di Wu , Chengshuai Shi , Jing Yang , Cong Shen

Ranking problems based on pairwise comparisons, such as those arising in online gaming, often involve a large pool of items to order. In these situations, the gap in performance between any two items can be significant, and the smallest and…

Statistics Theory · Mathematics 2022-06-16 Heejong Bong , Alessandro Rinaldo

In the context of reinforcement learning from human feedback (RLHF), the reward function is generally derived from maximum likelihood estimation of a random utility model based on pairwise comparisons made by humans. The problem of learning…

Computer Science and Game Theory · Computer Science 2024-11-08 Luise Ge , Daniel Halpern , Evi Micha , Ariel D. Procaccia , Itai Shapira , Yevgeniy Vorobeychik , Junlin Wu

Maximum likelihood estimators are often of limited practical use due to the intensive computation they require. We propose a family of alternative estimators that maximize a stochastic variation of the composite likelihood function. Each of…

Machine Learning · Computer Science 2010-03-04 Joshua V Dillon , Guy Lebanon

Large Language Models (LLMs) have shown impressive moral reasoning abilities. Yet they often diverge when confronted with complex, multi-factor moral dilemmas. To address these discrepancies, we propose a framework that synthesizes multiple…

Computation and Language · Computer Science 2026-02-09 Chenchen Yuan , Zheyu Zhang , Shuo Yang , Bardh Prenkaj , Gjergji Kasneci

Robust reinforcement learning aims to produce policies that have strong guarantees even in the face of environments/transition models whose parameters have strong uncertainty. Existing work uses value-based methods and the usual primitive…

Artificial Intelligence · Computer Science 2018-02-12 Daniel J. Mankowitz , Timothy A. Mann , Pierre-Luc Bacon , Doina Precup , Shie Mannor

While conventional ranking systems focus solely on maximizing the utility of the ranked items to users, fairness-aware ranking systems additionally try to balance the exposure for different protected attributes such as gender or race. To…

Machine Learning · Computer Science 2021-12-14 Omid Memarrast , Ashkan Rezaei , Rizal Fathony , Brian Ziebart

Many applications, e.g. in content recommendation, sports, or recruitment, leverage the comparisons of alternatives to score those alternatives. The classical Bradley-Terry model and its variants have been widely used to do so. The…

Methodology · Statistics 2024-02-23 Julien Fageot , Sadegh Farhadkhani , Lê Nguyên Hoang , Oscar Villemaud

Robust model predictive control algorithms are essential for addressing unavoidable errors due to the uncertainty in predicting real-world systems. However, the formulation of such algorithms typically results in a trade-off between…

Systems and Control · Electrical Eng. & Systems 2025-04-25 Moritz Heinlein , Sankaranarayanan Subramanian , Sergio Lucia

We study popularity for matchings under preferences. This solution concept captures matchings that do not lose against any other matching in a majority vote by the agents. A popular matching is said to be robust if it is popular among…

Data Structures and Algorithms · Computer Science 2025-10-23 Martin Bullinger , Gergely Csáji , Rohith Reddy Gangam , Parnian Shahkar

We address the problem of learning a ranking by using adaptively chosen pairwise comparisons. Our goal is to recover the ranking accurately but to sample the comparisons sparingly. If all comparison outcomes are consistent with the ranking,…

Machine Learning · Statistics 2017-06-16 Lucas Maystre , Matthias Grossglauser

In this paper, we study a popular method for inference of the Bradley-Terry model parameters, namely the MM algorithm, for maximum likelihood estimation and maximum a posteriori probability estimation. This class of models includes the…

Machine Learning · Statistics 2020-12-29 Milan Vojnovic , Seyoung Yun , Kaifang Zhou

Pluralistic alignment has emerged as a critical frontier in the development of Large Language Models (LLMs), with reward models (RMs) serving as a central mechanism for capturing diverse human values. While benchmarks for general response…

Computation and Language · Computer Science 2026-04-09 Qiyao Ma , Dechen Gao , Rui Cai , Boqi Zhao , Hanchu Zhou , Junshan Zhang , Zhe Zhao

We propose a method for evaluating the robustness of widely used LLM ranking systems -- variants of a Bradley--Terry model -- to dropping a worst-case very small fraction of preference data. Our approach is computationally fast and easy to…

Machine Learning · Statistics 2026-03-06 Jenny Y. Huang , Yunyi Shen , Dennis Wei , Tamara Broderick