English
Related papers

Related papers: NPO: Learning Alignment and Meta-Alignment through…

200 papers

Reward-based alignment methods for large language models (LLMs) face two key limitations: vulnerability to reward hacking, where models exploit flaws in the reward signal; and reliance on brittle, labor-intensive prompt engineering when…

Computation and Language · Computer Science 2025-05-20 Zae Myung Kim , Chanwoo Park , Vipul Raheja , Suin Kim , Dongyeop Kang

AI alignment in the shape of Reinforcement Learning from Human Feedback (RLHF) is increasingly treated as a crucial ingredient for high performance large language models. Proximal Policy Optimization (PPO) has been positioned by recent…

At the forefront of state-of-the-art human alignment methods are preference optimization methods (*PO). Prior research has often concentrated on identifying the best-performing method, typically involving a grid search over hyperparameters,…

Computation and Language · Computer Science 2025-04-30 Kian Ahrabian , Xihui Lin , Barun Patra , Vishrav Chaudhary , Alon Benhaim , Jay Pujara , Xia Song

Despite the importance of aligning language models with human preferences, crowd-sourced human feedback is often noisy -- for example, preferring less desirable responses -- posing a fundamental challenge to alignment. A truly robust…

Machine Learning · Computer Science 2025-10-27 Masahiro Fujisawa , Masaki Adachi , Michael A. Osborne

Learning from human preferences is crucial for language models (LMs) to effectively cater to human needs and societal values. Previous research has made notable progress by leveraging human feedback to follow instructions. However, these…

Computation and Language · Computer Science 2023-12-12 Jian Hu , Li Tao , June Yang , Chandler Zhou

Reinforcement learning from human feedback (RLHF) typically assumes a static or non-strategic reward model (RM). In iterative deployment, however, the policy generates the data on which the RM is retrained, creating a feedback loop.…

Machine Learning · Computer Science 2026-05-07 Etienne Gauthier , Francis Bach , Michael I. Jordan

Reinforcement learning from human feedback (RLHF) has emerged as the standard paradigm for aligning large language models with human preferences. However, reward-based methods grounded in the Bradley-Terry assumption struggle to capture the…

Artificial Intelligence · Computer Science 2026-04-08 Fang Wu , Xu Huang , Weihao Xuan , Zhiwei Zhang , Yijia Xiao , Guancheng Wan , Xiaomin Li , Bing Hu , Peng Xia , Jure Leskovec , Yejin Choi

Traditional RL algorithms like Proximal Policy Optimization (PPO) typically train on the entire rollout buffer, operating under the assumption that all generated episodes provide a beneficial optimization signal. However, these episodes…

Machine Learning · Computer Science 2026-04-03 Dong Shu , Denghui Zhang , Jessica Hullman

Reinforcement Learning from Human Feedback (RLHF) has shown promise in aligning large language models (LLMs). Yet its reliance on a singular reward model often overlooks the diversity of human preferences. Recent approaches address this…

Computation and Language · Computer Science 2025-07-23 Tianze Wang , Dongnan Gui , Yifan Hu , Shuhang Lin , Linjun Zhang

Reinforcement Learning with Human Feedback (RLHF) is the key to the success of large language models (LLMs) in recent years. In this work, we first introduce the concepts of knowledge breadth and knowledge depth, which measure the…

Computation and Language · Computer Science 2025-02-21 Sizhe Wang , Yongqi Tong , Hengyuan Zhang , Dawei Li , Xin Zhang , Tianlong Chen

Reinforcement learning in large language models (LLMs) often relies on scalar rewards, a practice that discards valuable textual rationale buried in the rollouts, forcing the model to explore \textit{de novo} with each attempt and hindering…

Machine Learning · Computer Science 2025-10-21 Ang Li , Yifei Wang , Zhihang Yuan , Stefanie Jegelka , Yisen Wang

DPO (Direct Preference Optimization) has become a widely used offline preference optimization algorithm due to its simplicity and training stability. However, DPO is prone to overfitting and collapse. To address these challenges, we propose…

Machine Learning · Computer Science 2025-08-26 Rui Wang , Qianguo Sun , Chao Song , Junlong Wu , Tianrong Chen , Zhiyun Zeng , Yu Li

In this paper, we aim to align large language models with the ever-changing, complex, and diverse human values (e.g., social norms) across time and locations. This presents a challenge to existing alignment techniques, such as supervised…

Computation and Language · Computer Science 2023-12-27 Chunpu Xu , Steffi Chern , Ethan Chern , Ge Zhang , Zekun Wang , Ruibo Liu , Jing Li , Jie Fu , Pengfei Liu

Recent advances in alignment techniques such as Supervised Fine-Tuning (SFT), Reinforcement Learning from Human Feedback (RLHF), and Direct Preference Optimization (DPO) have improved the safety of large language models (LLMs). However,…

Computation and Language · Computer Science 2026-02-26 Mengxuan Hu , Vivek V. Datla , Anoop Kumar , Zihan Guan , Sheng Li , Alfy Samuel , Daben Liu

Proximal Policy Optimization (PPO) is commonly used in Reinforcement Learning from Human Feedback to align large language models (LLMs) with downstream tasks. This paper investigates the feasibility of using PPO for direct reinforcement…

Computation and Language · Computer Science 2024-10-23 Alexander G. Padula , Dennis J. N. J. Soemers

Proximal Policy Optimization (PPO) has been positioned by recent literature as the canonical method for the RL part of Reinforcement Learning from Human Feedback (RLHF). PPO performs well empirically but has a heuristic motivation and…

Machine Learning · Computer Science 2026-02-10 Dipan Maity

Online alignment (e.g., GRPO) is generally more performant than offline alignment (e.g., DPO) -- but why? Drawing on prospect theory from behavioral economics, we propose a human-centric explanation. We prove that online on-policy sampling…

Artificial Intelligence · Computer Science 2026-03-30 Sijia Liu , Niklas Muennighoff , Kawin Ethayarajh

Reinforcement Learning from Human Feedback (RLHF) plays a crucial role in aligning large language models (LLMs) with human values and preferences. However, the quality and stability of the trained reward model largely determine the final…

Machine Learning · Computer Science 2025-12-17 Chunjin Jian , Xinhua Zhu

Direct Preference Optimization (DPO) has emerged as a more computationally efficient alternative to Reinforcement Learning from Human Feedback (RLHF) with Proximal Policy Optimization (PPO), eliminating the need for reward models and online…

Computation and Language · Computer Science 2024-10-28 Xin Mao , Feng-Lin Li , Huimin Xu , Wei Zhang , Wang Chen , Anh Tuan Luu

As Large Language Models (LLMs) are increasingly deployed in real-world applications, it is important to ensure their behaviors align with human values, societal norms, and ethical principles. However, safety alignment under Reinforcement…

Machine Learning · Computer Science 2026-02-02 Yifan Niu , Han Xiao , Dongyi Liu , Nuo Chen , Jia Li
‹ Prev 1 2 3 10 Next ›