English
Related papers

Related papers: Constitutional AI: Harmlessness from AI Feedback

200 papers

When a person is not satisfied with how a robot performs a task, they can intervene to correct it. Reward learning methods enable the robot to adapt its reward function online based on such human input, but they rely on handcrafted…

Robotics · Computer Science 2021-01-13 Andreea Bobu , Marius Wiggert , Claire Tomlin , Anca D. Dragan

As AI systems are increasingly incorporated into domains where human behavior has set the norm, a challenge for AI governance and AI alignment research is to regulate their behavior in a way that is useful and constructive for society. One…

Computers and Society · Computer Science 2024-06-10 Sunayana Rane

Large language models are increasingly integrated into decision-making in areas such as healthcare, law, finance, engineering, and government. Yet they share a critical limitation: they produce fluent outputs even when their internal…

Artificial Intelligence · Computer Science 2026-04-17 Rikard Rosenbacke , Carl Rosenbacke , Victor Rosenbacke , Martin McKee

Reinforcement Learning (RL) in environments with complex, history-dependent reward structures poses significant challenges for traditional methods. In this work, we introduce a novel approach that leverages automaton-based feedback to guide…

Machine Learning · Computer Science 2025-10-20 Mahyar Alinejad , Alvaro Velasquez , Yue Wang , George Atia

Unsupervised reinforcement learning (RL) aims at pre-training agents that can solve a wide range of downstream tasks in complex environments. Despite recent advancements, existing approaches suffer from several limitations: they may require…

A long-term goal of reinforcement learning is to design agents that can autonomously interact and learn in the world. A critical challenge to such autonomy is the presence of irreversible states which require external assistance to recover…

Machine Learning · Computer Science 2022-10-20 Annie Xie , Fahim Tajwar , Archit Sharma , Chelsea Finn

As artificial intelligence (AI) improves, traditional alignment strategies may falter in the face of unpredictable self-improvement, hidden subgoals, and the sheer complexity of intelligent systems. Inspired by contemplative wisdom…

Artificial Intelligence · Computer Science 2025-08-19 Ruben Laukkonen , Fionn Inglis , Shamil Chandaria , Lars Sandved-Smith , Edmundo Lopez-Sola , Jakob Hohwy , Jonathan Gold , Adam Elwood

Despite recent advances of AI research in many application-specific domains, we do not know how to build a human-level artificial intelligence (HLAI). We conjecture that learning from others' experience with the language is the essential…

Artificial Intelligence · Computer Science 2022-12-16 Deokgun Park , Md Ashaduzzaman Rubel Mondol , Aishwarya Pothula , Mazharul Islam

Techniques based on Reinforcement Learning (RL) are increasingly being used to design control policies for robotic systems. RL fundamentally relies on state-based reward functions to encode desired behavior of the robot and bad reward…

Robotics · Computer Science 2020-11-11 Parv Kapoor , Anand Balakrishnan , Jyotirmoy V. Deshmukh

With the development of large language models (LLMs), striking a balance between the performance and safety of AI systems has never been more critical. However, the inherent tension between the objectives of helpfulness and harmlessness…

Artificial Intelligence · Computer Science 2023-10-20 Josef Dai , Xuehai Pan , Ruiyang Sun , Jiaming Ji , Xinbo Xu , Mickel Liu , Yizhou Wang , Yaodong Yang

Institutional decisions -- regulatory compliance, clinical triage, prior authorization appeal -- require a different AI architecture than general-purpose agents provide. Agent frameworks infer authority conversationally, reconstruct…

Artificial Intelligence · Computer Science 2026-04-14 Mamadou Seck

Continuous-time reinforcement learning (CTRL) provides a natural framework for sequential decision-making in dynamic environments where interactions evolve continuously over time. While CTRL has shown growing empirical success, its ability…

Machine Learning · Computer Science 2025-12-04 Runze Zhao , Yue Yu , Ruhan Wang , Chunfeng Huang , Dongruo Zhou

Prescriptive Process Monitoring is a prominent problem in Process Mining, which consists in identifying a set of actions to be recommended with the goal of optimising a target measure of interest or Key Performance Indicator (KPI). One…

Artificial Intelligence · Computer Science 2025-07-25 Stefano Branchi , Andrei Buliga , Chiara Di Francescomarino , Chiara Ghidini , Francesca Meneghello , Massimiliano Ronzani

Autonomous Artificial Intelligence (AI) has many benefits. It also has many risks. In this work, we identify the 3 levels of autonomous AI. We are of the position that AI must not be fully autonomous because of the many risks, especially as…

Artificial Intelligence · Computer Science 2025-08-01 Tosin Adewumi , Lama Alkhaled , Florent Imbert , Hui Han , Nudrat Habib , Karl Löwenmark

Reinforcement learning (RL) algorithms face significant challenges when dealing with long-horizon robot manipulation tasks in real-world environments due to sample inefficiency and safety issues. To overcome these challenges, we propose a…

Robotics · Computer Science 2023-08-03 Ayano Hiranaka , Minjune Hwang , Sharon Lee , Chen Wang , Li Fei-Fei , Jiajun Wu , Ruohan Zhang

AI-enabled capabilities are reaching the requisite level of maturity to be deployed in the real world, yet do not always make correct or safe decisions. One way of addressing these concerns is to leverage AI control systems alongside and in…

Machine Learning · Computer Science 2024-10-10 Walt Woods , Alexander Grushin , Simon Khan , Alvaro Velasquez

Military weapon systems and command-and-control infrastructure augmented by artificial intelligence (AI) have seen rapid development and deployment in recent years. However, the sociotechnical impacts of AI on combat systems, military…

Computers and Society · Computer Science 2025-11-13 Riley Simmons-Edler , Jean Dong , Paul Lushenko , Kanaka Rajan , Ryan P. Badman

Text classification models are typically trained via supervised fine-tuning (SFT). However, SFT essentially performs behavior cloning from instance-wise labels and thus fails to adequately capture relative preference relations among…

Machine Learning · Computer Science 2026-05-19 Tianxiang Xu , Xiaoyan Zhu , Xin Lai , Jiayin Wang

As LLM-based systems increasingly operate as agents embedded within human social and technical systems, alignment can no longer be treated as a property of an isolated model, but must be understood in relation to the environments in which…

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