English
Related papers

Related papers: What Does Preference Learning Recover from Pairwis…

200 papers

We study the post-training of large language models (LLMs) with human preference data. Recently, direct preference optimization and its variants have shown considerable promise in aligning language models, eliminating the need for reward…

Machine Learning · Computer Science 2025-05-14 Teng Xiao , Zhen Ge , Sujay Sanghavi , Tian Wang , Julian Katz-Samuels , Marc Versage , Qingjun Cui , Trishul Chilimbi

This paper investigates the integration of response time data into human preference learning frameworks for more effective reward model elicitation. While binary preference data has become fundamental in fine-tuning foundation models,…

Machine Learning · Computer Science 2025-10-29 Ayush Sawarni , Sahasrajit Sarmasarkar , Vasilis Syrgkanis

Current instruction-tuned language models are exclusively trained with textual preference data and thus are often not aligned with the unique requirements of other modalities, such as speech. To better align language models with the speech…

Safe reinforcement learning (RL) is a standard paradigm for safety-critical decision making. However, real-world safety constraints can be complex, subjective, and even hard to explicitly specify. Existing works on constraint inference rely…

Machine Learning · Computer Science 2026-05-25 Chenglin Li , Grant Ruan , Hua Geng

This paper presents a novel technique for incorporating user input when learning and inferring user preferences. When trying to provide users of black-box machine learning models with actionable recourse, we often wish to incorporate their…

Machine Learning · Computer Science 2024-09-24 Kaivalya Rawal , Himabindu Lakkaraju

Preference-Based reinforcement learning (PBRL) learns directly from the preferences of human teachers regarding agent behaviors without needing meticulously designed reward functions. However, existing PBRL methods often learn primarily…

Machine Learning · Computer Science 2024-10-16 Ziang Liu , Junjie Xu , Xingjiao Wu , Jing Yang , Liang He

Preference-based many-objective optimization faces two obstacles: an expanding space of trade-offs and heterogeneous, context-dependent human value structures. Towards this, we propose a Bayesian framework that learns a small set of latent…

Machine Learning · Computer Science 2026-03-31 Manisha Dubey , Sebastiaan De Peuter , Wanrong Wang , Samuel Kaski

Many applications such as recommendation systems or sports tournaments involve pairwise comparisons within a collection of $n$ items, the goal being to aggregate the binary outcomes of the comparisons in order to recover the latent strength…

Statistics Theory · Mathematics 2023-07-13 Eglantine Karlé , Hemant Tyagi

As large language models (LLMs) are increasingly used as evaluators for natural language generation tasks, ensuring unbiased assessments is essential. However, LLM evaluators often display biased preferences, such as favoring verbosity and…

Computation and Language · Computer Science 2025-04-21 Hawon Jeong , ChaeHun Park , Jimin Hong , Hojoon Lee , Jaegul Choo

Learning from preference-based feedback has recently gained considerable traction as a promising approach to align generative models with human interests. Instead of relying on numerical rewards, the generative models are trained using…

Machine Learning · Computer Science 2023-10-31 Sayak Ray Chowdhury , Xingyu Zhou , Nagarajan Natarajan

Preference optimization methods such as DPO and KTO are widely used for aligning language models, yet little is understood about what properties of preference data drive downstream reasoning gains. We ask: what aspects of a preference pair…

Computation and Language · Computer Science 2026-04-13 Chia-Hsuan Lee , Mingyang Zhou , Renkun Ni , Zelei Cheng , Sihui Dai , Supriyo Chakraborty , Shixiong Zhang , Sambit Sahu , William Campbell

Humans use social context to specify preferences over behaviors, i.e. their reward functions. Yet, algorithms for inferring reward models from preference data do not take this social learning view into account. Inspired by pragmatic human…

Machine Learning · Computer Science 2024-05-24 Andi Peng , Yuying Sun , Tianmin Shu , David Abel

In preference-based reinforcement learning (RL), an agent interacts with the environment while receiving preferences instead of absolute feedback. While there is increasing research activity in preference-based RL, the design of formal…

Machine Learning · Computer Science 2020-06-30 Ellen R. Novoseller , Yibing Wei , Yanan Sui , Yisong Yue , Joel W. Burdick

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…

The Bradley-Terry model is widely used for the analysis of pairwise comparison data and, in essence, produces a ranking of the items under comparison. We embed the Bradley-Terry model within a stochastic block model, allowing items to…

Methodology · Statistics 2025-11-06 Lapo Santi , Nial Friel

Reward modeling is a key step in building safe foundation models when applying reinforcement learning from human feedback (RLHF) to align Large Language Models (LLMs). However, reward modeling based on the Bradley-Terry (BT) model assumes a…

Artificial Intelligence · Computer Science 2025-09-24 Jingyan Shen , Jiarui Yao , Rui Yang , Yifan Sun , Feng Luo , Rui Pan , Tong Zhang , Han Zhao

To enhance the performance of the recommender system, side information is extensively explored with various features (e.g., visual features and textual features). However, there are some demerits of side information: (1) the extra data is…

Information Retrieval · Computer Science 2019-05-03 Wenhui Yu , Zheng Qin

Accurately aligning large language models (LLMs) with human preferences is crucial for informing fair, economically sound, and statistically efficient decision-making processes. However, we argue that the predominant approach for aligning…

Machine Learning · Statistics 2025-08-26 Jiancong Xiao , Ziniu Li , Xingyu Xie , Emily Getzen , Cong Fang , Qi Long , Weijie J. Su

Preference-based Reinforcement Learning (PbRL) is a paradigm in which an RL agent learns to optimize a task using pair-wise preference-based feedback over trajectories, rather than explicit reward signals. While PbRL has demonstrated…

Machine Learning · Computer Science 2024-04-18 Wenhao Zhan , Masatoshi Uehara , Wen Sun , Jason D. Lee

This technical report studies the problem of ranking from pairwise comparisons in the classical Bradley-Terry-Luce (BTL) model, with a focus on score estimation. For general graphs, we show that, with sufficiently many samples, maximum…

Machine Learning · Statistics 2023-04-17 Yanxi Chen