English
Related papers

Related papers: Axioms for AI Alignment from Human Feedback

200 papers

We argue for the epistemic and ethical advantages of pluralism in Reinforcement Learning from Human Feedback (RLHF) in the context of Large Language Models (LLM). Drawing on social epistemology and pluralist philosophy of science, we…

Computers and Society · Computer Science 2025-05-27 Kristian González Barman , Simon Lohse , Henk de Regt

Reinforcement Learning from Human Feedback relies on reward models to align large language models with human preferences. However, RLHF often suffers from reward hacking, wherein policy learning exploits flaws in the trained reward model to…

Machine Learning · Computer Science 2025-05-20 Kangwen Zhao , Jianfeng Cai , Jinhua Zhu , Ruopei Sun , Dongyun Xue , Wengang Zhou , Li Li , Houqiang Li

Reinforcement learning from human feedback (RLHF) and, at its core, reward modeling have become a crucial part of training powerful large language models (LLMs). One commonly overlooked factor in training high-quality reward models (RMs) is…

Computation and Language · Computer Science 2025-05-19 Kian Ahrabian , Pegah Jandaghi , Negar Mokhberian , Sai Praneeth Karimireddy , Jay Pujara

This paper presents Multi-Objective Reinforcement Learning from AI Feedback (MORLAIF), a novel approach to improving the alignment and performance of language models trained using reinforcement learning from AI feedback (RLAIF). In contrast…

Machine Learning · Computer Science 2024-06-13 Marcus Williams

Reinforcement learning from human feedback (RLHF) emerges as a promising paradigm for aligning large language models (LLMs). However, a notable challenge in RLHF is overoptimization, where beyond a certain threshold, the pursuit of higher…

Machine Learning · Computer Science 2024-01-02 Yuanzhao Zhai , Han Zhang , Yu Lei , Yue Yu , Kele Xu , Dawei Feng , Bo Ding , Huaimin Wang

Foundation models, specifically Large Language Models (LLMs), have lately gained wide-spread attention and adoption. Reinforcement Learning with Human Feedback (RLHF) involves training a reward model to capture desired behaviors, which is…

Computation and Language · Computer Science 2024-01-25 Will LeVine , Benjamin Pikus , Anthony Chen , Sean Hendryx

Reward functions are a common way to specify the objective of a robot. As designing reward functions can be extremely challenging, a more promising approach is to directly learn reward functions from human teachers. Importantly, data from…

In light of the challenges and costs of real-world testing, autonomous vehicle developers often rely on testing in simulation for the creation of reliable systems. A key element of effective simulation is the incorporation of realistic…

Artificial Intelligence · Computer Science 2023-09-06 Yulong Cao , Boris Ivanovic , Chaowei Xiao , Marco Pavone

Learning from human feedback is a popular approach to train robots to adapt to user preferences and improve safety. Existing approaches typically consider a single querying (interaction) format when seeking human feedback and do not…

Robotics · Computer Science 2026-01-16 Yashwanthi Anand , Nnamdi Nwagwu , Kevin Sabbe , Naomi T. Fitter , Sandhya Saisubramanian

Recently, tremendous strides have been made to align the generation of Large Language Models (LLMs) with human values to mitigate toxic or unhelpful content. Leveraging Reinforcement Learning from Human Feedback (RLHF) proves effective and…

Computation and Language · Computer Science 2024-06-05 Mingye Zhu , Yi Liu , Lei Zhang , Junbo Guo , Zhendong Mao

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

We posit that to achieve continual model improvement and multifaceted alignment, future models must learn from natural human interaction. Current conversational models are aligned using pre-annotated, expert-generated human feedback. In…

Artificial Intelligence · Computer Science 2025-09-30 Chuanyang Jin , Jing Xu , Bo Liu , Leitian Tao , Olga Golovneva , Tianmin Shu , Wenting Zhao , Xian Li , Jason Weston

Reinforcement Learning from Human Feedback (RLHF) is widely used for aligning large language models, yet practitioners face a persistent puzzle: improving safety often reduces fairness, scaling to diverse populations becomes computationally…

Machine Learning · Computer Science 2025-11-26 Subramanyam Sahoo , Aman Chadha , Vinija Jain , Divya Chaudhary

Past analyses of reinforcement learning from human feedback (RLHF) assume that the human evaluators fully observe the environment. What happens when human feedback is based only on partial observations? We formally define two failure cases:…

Machine Learning · Computer Science 2024-11-19 Leon Lang , Davis Foote , Stuart Russell , Anca Dragan , Erik Jenner , Scott Emmons

Reinforcement learning from human or AI feedback (RLHF/RLAIF) for speech-in/speech-out dialogue systems (SDS) remains underexplored, with prior work largely limited to single semantic rewards applied at the utterance level. Such setups…

Computation and Language · Computer Science 2026-01-28 Siddhant Arora , Jinchuan Tian , Jiatong Shi , Hayato Futami , Yosuke Kashiwagi , Emiru Tsunoo , Shinji Watanabe

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

Reinforcement learning from human feedback (RLHF) has contributed to performance improvements in large language models. To tackle its reliance on substantial amounts of human-labeled data, a successful approach is multi-task representation…

Machine Learning · Computer Science 2025-03-06 Ruitao Chen , Liwei Wang

Reinforcement Learning from Human Feedback (RLHF) is a crucial technique for aligning language models with human preferences, playing a pivotal role in the success of conversational models like GPT-4, ChatGPT, and Llama 2. A core challenge…

Computation and Language · Computer Science 2025-06-04 Chenghua Huang , Zhizhen Fan , Lu Wang , Fangkai Yang , Pu Zhao , Zeqi Lin , Qingwei Lin , Dongmei Zhang , Saravan Rajmohan , Qi Zhang

Reinforcement Learning frameworks, particularly those utilizing human annotations, have become an increasingly popular method for preference fine-tuning, where the outputs of a language model are tuned to match a certain set of behavioral…

Machine Learning · Computer Science 2025-10-21 Archie Chaudhury

Reinforcement Learning from Human Feedback (RLHF) has enabled significant advancements within language modeling for powerful, instruction-following models. However, the alignment of these models remains a pressing challenge as the policy…

Machine Learning · Computer Science 2024-06-21 Ahmed M. Ahmed , Rafael Rafailov , Stepan Sharkov , Xuechen Li , Sanmi Koyejo
‹ Prev 1 8 9 10 Next ›