English
Related papers

Related papers: Capturing Individual Human Preferences with Reward…

200 papers

Reward models (RMs) play a pivotal role in aligning large language models (LLMs) with human values. However, noisy preferences in human feedback can lead to reward misgeneralization - a phenomenon where reward models learn spurious…

Reinforcement Learning from Human Feedback (RLHF) allows us to train models, such as language models (LMs), to follow complex human preferences. In RLHF for LMs, we first train an LM using supervised fine-tuning, sample pairs of responses,…

Machine Learning · Computer Science 2025-07-22 Johannes Ackermann , Takashi Ishida , Masashi Sugiyama

In the physical world, people have dynamic preferences, e.g., the same situation can lead to satisfaction for some humans and to frustration for others. Personalization is called for. The same observation holds for online behavior with…

Information Retrieval · Computer Science 2017-08-16 Ziming Li , Julia Kiseleva , Maarten de Rijke , Artem Grotov

In this paper, we take a step towards a deeper understanding of learning from human preferences by systematically comparing the paradigm of reinforcement learning from human feedback (RLHF) with the recently proposed paradigm of direct…

Machine Learning · Computer Science 2024-06-06 Andi Nika , Debmalya Mandal , Parameswaran Kamalaruban , Georgios Tzannetos , Goran Radanović , Adish Singla

A shortcoming of batch reinforcement learning is its requirement for rewards in data, thus not applicable to tasks without reward functions. Existing settings for lack of reward, such as behavioral cloning, rely on optimal demonstrations…

Machine Learning · Computer Science 2022-11-30 Guoxi Zhang , Hisashi Kashima

Human feedback often arrives as preferences rather than calibrated numeric rewards, motivating reinforcement learning from preferential feedback, also referred to as reinforcement learning from human feedback (RLHF). We present a rigorous…

Machine Learning · Statistics 2026-05-26 Nikola Pavlovic , Sattar Vakili , Qing Zhao

Reinforcement Learning from Human Feedback (RLHF) facilitates the alignment of large language models with human preferences, significantly enhancing the quality of interactions between humans and models. InstructGPT implements RLHF through…

Computation and Language · Computer Science 2023-10-10 Zheng Yuan , Hongyi Yuan , Chuanqi Tan , Wei Wang , Songfang Huang , Fei Huang

Recent work introduced the model of learning from discriminative feature feedback, in which a human annotator not only provides labels of instances, but also identifies discriminative features that highlight important differences between…

Machine Learning · Computer Science 2021-05-25 Sanjoy Dasgupta , Sivan Sabato

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

Aligning human preference and value is an important requirement for contemporary foundation models. State-of-the-art techniques such as Reinforcement Learning from Human Feedback (RLHF) often consist of two stages: 1) supervised fine-tuning…

Artificial Intelligence · Computer Science 2024-10-29 Jiaxiang Li , Siliang Zeng , Hoi-To Wai , Chenliang Li , Alfredo Garcia , Mingyi Hong

Reward design is a fundamental problem in reinforcement learning (RL). A misspecified or poorly designed reward can result in low sample efficiency and undesired behaviors. In this paper, we propose the idea of programmatic reward design,…

Machine Learning · Computer Science 2022-01-10 Weichao Zhou , Wenchao Li

Reinforcement learning from human feedback (RLHF) is a widely used method for aligning large language models with human preferences. However, RLHF often suffers from reward model overoptimisation, in which models overfit to the reward…

Machine Learning · Computer Science 2025-09-30 Lorenz Wolf , Robert Kirk , Mirco Musolesi

Aligning large language models (LLMs) with human values and intents critically involves the use of human or AI feedback. While dense feedback annotations are expensive to acquire and integrate, sparse feedback presents a structural design…

Machine Learning · Computer Science 2024-02-07 Hritik Bansal , John Dang , Aditya Grover

Reinforcement Learning with Human Feedback (RLHF) has emerged as a key paradigm for task-specific fine-tuning of language models using human preference data. While numerous publicly available preference datasets provide pairwise comparisons…

Computation and Language · Computer Science 2025-11-03 Ashwin Kumar , Yuzi He , Aram H. Markosyan , Bobbie Chern , Imanol Arrieta-Ibarra

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

Reinforcement learning from human feedback (RLHF) is a variant of reinforcement learning (RL) that learns from human feedback instead of relying on an engineered reward function. Building on prior work on the related setting of…

Machine Learning · Computer Science 2025-12-30 Timo Kaufmann , Paul Weng , Viktor Bengs , Eyke Hüllermeier

Understanding human preferences is crucial for improving foundation models and building personalized AI systems. However, preferences are inherently diverse and complex, making it difficult for traditional reward models to capture their…

Artificial Intelligence · Computer Science 2025-06-12 Feng Luo , Rui Yang , Hao Sun , Chunyuan Deng , Jiarui Yao , Jingyan Shen , Huan Zhang , Hanjie Chen

Aligning human preference and value is an important requirement for building contemporary foundation models and embodied AI. However, popular approaches such as reinforcement learning with human feedback (RLHF) break down the task into…

Artificial Intelligence · Computer Science 2024-12-03 Chenliang Li , Siliang Zeng , Zeyi Liao , Jiaxiang Li , Dongyeop Kang , Alfredo Garcia , Mingyi Hong

While finetuning language models from pairwise preferences has proven remarkably effective, the underspecified nature of natural language presents critical challenges. Direct preference feedback is uninterpretable, difficult to provide…

Computation and Language · Computer Science 2024-11-07 Silviu Pitis , Ziang Xiao , Nicolas Le Roux , Alessandro Sordoni

Great success has been reported using Reinforcement Learning from Human Feedback (RLHF) to align large language models, with open preference datasets enabling wider experimentation, particularly for "helpfulness" in tasks like dialogue and…

Computation and Language · Computer Science 2024-07-12 Prasann Singhal , Tanya Goyal , Jiacheng Xu , Greg Durrett