English
Related papers

Related papers: Aligning to What? Limits to RLHF Based Alignment

200 papers

Reinforcement Learning from Human Feedback (RLHF) is an effective approach for aligning language models to human preferences. Central to RLHF is learning a reward function for scoring human preferences. Two main approaches for learning a…

Personalized large language models (LLMs) are designed to tailor responses to individual user preferences. While Reinforcement Learning from Human Feedback (RLHF) is a commonly used framework for aligning LLMs with human preferences,…

Computation and Language · Computer Science 2024-12-10 Xinyu Li , Ruiyang Zhou , Zachary C. Lipton , Liu Leqi

Reinforcement learning from human feedback (RLHF) is a prevalent approach to align AI systems with human values by learning rewards from human preference data. Due to various reasons, however, such data typically takes the form of rankings…

Machine Learning · Computer Science 2024-06-06 Ilgee Hong , Zichong Li , Alexander Bukharin , Yixiao Li , Haoming Jiang , Tianbao Yang , Tuo Zhao

Reinforcement learning from human feedback (RLHF) has emerged as the primary method for aligning large language models (LLMs) with human preferences. While it enables LLMs to achieve human-level alignment, it often incurs significant…

Computation and Language · Computer Science 2025-03-21 Shivank Garg , Ayush Singh , Shweta Singh , Paras Chopra

Large language models (LLMs) are used to generate content for a wide range of tasks, and are set to reach a growing audience in coming years due to integration in product interfaces like ChatGPT or search engines like Bing. This intensifies…

Computation and Language · Computer Science 2023-03-10 Hannah Rose Kirk , Bertie Vidgen , Paul Röttger , Scott A. Hale

Reinforcement learning from human feedback (RLHF) is a recent technique to improve the quality of the text generated by a language model, making it closer to what humans would generate. A core ingredient in RLHF's success in aligning and…

Computation and Language · Computer Science 2024-07-08 Miguel Moura Ramos , Patrick Fernandes , António Farinhas , André F. T. Martins

Multi-objective alignment from human feedback (MOAHF) in large language models (LLMs) is a challenging problem as human preferences are complex, multifaceted, and often conflicting. Recent works on MOAHF considered a-priori multi-objective…

Machine Learning · Computer Science 2024-12-10 Subhojyoti Mukherjee , Anusha Lalitha , Sailik Sengupta , Aniket Deshmukh , Branislav Kveton

Reinforcement learning from human feedback (RLHF) has evolved to be one of the main methods for fine-tuning large language models (LLMs). However, existing RLHF methods are non-robust, and their performance deteriorates if the downstream…

Machine Learning · Computer Science 2025-03-04 Debmalya Mandal , Paulius Sasnauskas , Goran Radanovic

Large language models (LLMs) often contain misleading content, emphasizing the need to align them with human values to ensure secure AI systems. Reinforcement learning from human feedback (RLHF) has been employed to achieve this alignment.…

Computation and Language · Computer Science 2024-02-28 Feifan Song , Bowen Yu , Minghao Li , Haiyang Yu , Fei Huang , Yongbin Li , Houfeng Wang

Reinforcement Learning from Human Feedback (RLHF) is the prevailing approach to ensure Large Language Models (LLMs) align with human values. However, existing RLHF methods require a high computational cost, one main reason being that RLHF…

Computation and Language · Computer Science 2024-03-08 Yu Zhu , Chuxiong Sun , Wenfei Yang , Wenqiang Wei , Bo Tang , Tianzhu Zhang , Zhiyu Li , Shifeng Zhang , Feiyu Xiong , Jie Hu , Mingchuan yang

Reinforcement Learning from Human Feedback aligns the outputs of Large Language Models with human values and preferences. Central to this process is the reward model (RM), which translates human feedback into training signals for optimising…

Artificial Intelligence · Computer Science 2025-09-23 Zeyu Huang , Zihan Qiu , Zili Wang , Edoardo M. Ponti , Ivan Titov

The demand for regulating potentially risky behaviors of large language models (LLMs) has ignited research on alignment methods. Since LLM alignment heavily relies on reward models for optimization or evaluation, neglecting the quality of…

Computation and Language · Computer Science 2024-10-01 Yan Liu , Xiaoyuan Yi , Xiaokang Chen , Jing Yao , Jingwei Yi , Daoguang Zan , Zheng Liu , Xing Xie , Tsung-Yi Ho

Alignment of large language models (LLMs) has predominantly relied on pairwise preference optimization, where annotators select the better of two responses to a prompt. While simple, this approach overlooks the opportunity to learn from…

Machine Learning · Computer Science 2026-02-11 Yuxuan Tang , Yifan Feng

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

Existing approaches to language model alignment often treat safety as a tradeoff against helpfulness, which can lead to unacceptable responses in sensitive domains. To ensure reliable performance in such settings, we propose High-Confidence…

Machine Learning · Computer Science 2025-06-11 Yaswanth Chittepu , Blossom Metevier , Will Schwarzer , Austin Hoag , Scott Niekum , Philip S. Thomas

This study evaluates Direct Preference Optimization (DPO) and its variants for aligning Large Language Models (LLMs) with human preferences, testing three configurations: (1) with Supervised Fine Tuning (SFT), (2) without SFT, and (3)…

Computation and Language · Computer Science 2025-02-11 Amir Saeidi , Shivanshu Verma , Md Nayem Uddin , Chitta Baral

Reinforcement Learning from Human Feedback (RLHF) has been commonly used to align the behaviors of Large Language Models (LLMs) with human preferences. Recently, a popular alternative is Direct Policy Optimization (DPO), which replaces an…

Computation and Language · Computer Science 2024-06-03 Runsheng Yu , Yong Wang , Xiaoqi Jiao , Youzhi Zhang , James T. Kwok

Alignment is a crucial step to enhance the instruction-following and conversational abilities of language models. Despite many recent work proposing new algorithms, datasets, and training pipelines, there is a lack of comprehensive studies…

Computation and Language · Computer Science 2024-10-04 Xiao Yu , Qingyang Wu , Yu Li , Zhou Yu

Reinforcement Learning from Human Feedback (RLHF) is a widely used framework for the training of language models. However, the process of using RLHF to develop a language model that is well-aligned presents challenges, especially when it…

Computation and Language · Computer Science 2024-04-09 Bowen Qin , Duanyu Feng , Xi Yang

A key technology for the development of large language models (LLMs) involves instruction tuning that helps align the models' responses with human expectations to realize impressive learning abilities. Two major approaches for instruction…

Computation and Language · Computer Science 2023-08-03 Viet Dac Lai , Chien Van Nguyen , Nghia Trung Ngo , Thuat Nguyen , Franck Dernoncourt , Ryan A. Rossi , Thien Huu Nguyen