English
Related papers

Related papers: Human Preferences as Dueling Bandits

200 papers

Large foundation models pretrained on raw web-scale data are not readily deployable without additional step of extensive alignment to human preferences. Such alignment is typically done by collecting large amounts of pairwise comparisons…

Machine Learning · Computer Science 2024-06-13 Daiwei Chen , Yi Chen , Aniket Rege , Ramya Korlakai Vinayak

Most bandit policies are designed to either minimize regret in any problem instance, making very few assumptions about the underlying environment, or in a Bayesian sense, assuming a prior distribution over environment parameters. The former…

Machine Learning · Computer Science 2021-01-07 Branislav Kveton , Martin Mladenov , Chih-Wei Hsu , Manzil Zaheer , Csaba Szepesvari , Craig Boutilier

Learning to rank is an effective recommendation approach since its introduction around 2010. Famous algorithms such as Bayesian Personalized Ranking and Collaborative Less is More Filtering have left deep impact in both academia and…

Information Retrieval · Computer Science 2022-12-21 Hao Wang

Pairwise preference data have played an important role in the alignment of large language models (LLMs). Each sample of such data consists of a prompt, two different responses to the prompt, and a binary label indicating which of the two…

Computation and Language · Computer Science 2026-05-12 Zhongze Cai , Xiaocheng Li

Reinforcement learning from human feedback usually models preferences using a reward function that does not distinguish between people. We argue that this is unlikely to be a good design choice in contexts with high potential for…

Suppose that we wish to estimate a user's preference vector $w$ from paired comparisons of the form "does user $w$ prefer item $p$ or item $q$?," where both the user and items are embedded in a low-dimensional Euclidean space with distances…

Machine Learning · Statistics 2019-05-27 Gregory H. Canal , Andrew K. Massimino , Mark A. Davenport , Christopher J. Rozell

Learning from human feedback has enabled the alignment of language models (LMs) with human preferences. However, collecting human preferences is expensive and time-consuming, with highly variable annotation quality. An appealing alternative…

There are many applications in which it is desirable to order rather than classify instances. Here we consider the problem of learning how to order instances given feedback in the form of preference judgments, i.e., statements to the effect…

Machine Learning · Computer Science 2011-05-30 W. W. Cohen , R. E. Schapire , Y. Singer

Deciding which large language model (LLM) to use is a complex challenge. Pairwise ranking has emerged as a new method for evaluating human preferences for LLMs. This approach entails humans evaluating pairs of model outputs based on a…

Computation and Language · Computer Science 2025-02-18 Roland Daynauth , Christopher Clarke , Krisztian Flautner , Lingjia Tang , Jason Mars

Existing observational approaches for learning human preferences, such as inverse reinforcement learning, usually make strong assumptions about the observability of the human's environment. However, in reality, people make many important…

Machine Learning · Statistics 2021-10-29 Cassidy Laidlaw , Stuart Russell

Bayesian Personalized Ranking (BPR) is a representative pairwise learning method for optimizing recommendation models. It is widely known that the performance of BPR depends largely on the quality of negative sampler. In this paper, we make…

Information Retrieval · Computer Science 2018-09-24 Jingtao Ding , Guanghui Yu , Xiangnan He , Yong Li , Depeng Jin

We study a general multi-dueling bandit problem, where an agent compares multiple options simultaneously and aims to minimize the regret due to selecting suboptimal arms. This setting generalizes the traditional two-dueling bandit problem…

Machine Learning · Computer Science 2022-11-21 Yihan Du , Siwei Wang , Longbo Huang

Given a set of pairwise comparisons, the classical ranking problem computes a single ranking that best represents the preferences of all users. In this paper, we study the problem of inferring individual preferences, arising in the context…

Machine Learning · Statistics 2015-12-18 Rui Wu , Jiaming Xu , R. Srikant , Laurent Massoulié , Marc Lelarge , Bruce Hajek

Learning preferences implicit in the choices humans make is a well studied problem in both economics and computer science. However, most work makes the assumption that humans are acting (noisily) optimally with respect to their preferences.…

Machine Learning · Computer Science 2019-01-28 Lawrence Chan , Dylan Hadfield-Menell , Siddhartha Srinivasa , Anca Dragan

The question of aggregating pair-wise comparisons to obtain a global ranking over a collection of objects has been of interest for a very long time: be it ranking of online gamers (e.g. MSR's TrueSkill system) and chess players, aggregating…

Machine Learning · Computer Science 2015-11-13 Sahand Negahban , Sewoong Oh , Devavrat Shah

Deep Neural Network classifiers are vulnerable to adversarial attack, where an imperceptible perturbation could result in misclassification. However, the vulnerability of DNN-based image ranking systems remains under-explored. In this…

Computer Vision and Pattern Recognition · Computer Science 2021-06-08 Mo Zhou , Le Wang , Zhenxing Niu , Qilin Zhang , Nanning Zheng , Gang Hua

Determining a winner among a set of items using active pairwise comparisons under a limited budget is a challenging problem in preference-based learning. The goal of this study is to implement and evaluate the PARWiS algorithm, which shows…

Machine Learning · Computer Science 2026-03-03 Shailendra Bhandari

The $K$-armed dueling bandits problem, where the feedback is in the form of noisy pairwise preferences, has been widely studied due its applications in information retrieval, recommendation systems, etc. Motivated by concerns that user…

Machine Learning · Computer Science 2024-01-26 Joe Suk , Arpit Agarwal

Cascading bandits have gained popularity in recent years due to their applicability to recommendation systems and online advertising. In the cascading bandit model, at each timestep, an agent recommends an ordered subset of items (called an…

Machine Learning · Computer Science 2024-04-09 Yihan Du , R. Srikant , Wei Chen

In this paper, we construct and compare algorithmic approaches to solve the Preference Consistency Problem for preference statements based on hierarchical models. Instances of this problem contain a set of preference statements that are…

Logic in Computer Science · Computer Science 2024-11-01 Anne-Marie George , Nic Wilson , Barry O'Sullivan