English
Related papers

Related papers: Asymptotic Universal Alignment: A New Alignment Fr…

200 papers

Frontier AI systems, including large language models (LLMs), hold increasing influence over the epistemology of human users. Such influence can reinforce prevailing societal values, potentially contributing to the lock-in of misguided moral…

Machine Learning · Computer Science 2024-11-01 Tianyi Qiu , Yang Zhang , Xuchuan Huang , Jasmine Xinze Li , Jiaming Ji , Yaodong Yang

A core challenge in the development of increasingly capable AI systems is to make them safe and reliable by ensuring their behaviour is consistent with human values. This challenge, known as the alignment problem, does not merely apply to…

Machine Learning · Computer Science 2023-11-07 Raphaël Millière

Mean-field games have been used as a theoretical tool to obtain an approximate Nash equilibrium for symmetric and anonymous $N$-player games. However, limiting applicability, existing theoretical results assume variations of a "population…

Optimization and Control · Mathematics 2023-06-12 Batuhan Yardim , Semih Cayci , Matthieu Geist , Niao He

Computing Nash equilibrium policies is a central problem in multi-agent reinforcement learning that has received extensive attention both in theory and in practice. However, provable guarantees have been thus far either limited to fully…

Ensuring that AI systems make strategic decisions aligned with the specified preferences in adversarial sequential interactions is a critical challenge for developing trustworthy AI systems, especially when the environment is stochastic and…

Computer Science and Game Theory · Computer Science 2025-01-28 Abhishek Ninad Kulkarni , Jie Fu , Ufuk Topcu

LLM alignment ensures that large language models behave safely and effectively by aligning their outputs with human values, goals, and intentions. Aligning LLMs employ huge amounts of data, computation, and time. Moreover, curating data…

Machine Learning · Computer Science 2025-02-19 Amrit Khera , Rajat Ghosh , Debojyoti Dutta

Large Language Models (LLMs) have demonstrated remarkable adaptability, showcasing their capacity to excel in tasks for which they were not explicitly trained. However, despite their impressive natural language processing (NLP)…

Computation and Language · Computer Science 2023-09-08 Supun Manathunga , Isuru Hettigoda

Alignment of large language models (LLMs) typically involves training a reward model on preference data, followed by policy optimization with respect to the reward model. However, optimizing policies with respect to a single reward model…

Machine Learning · Computer Science 2025-07-23 Debangshu Banerjee , Kintan Saha , Aditya Gopalan

We introduce Robust Multi-Objective Decoding (RMOD), a novel inference-time algorithm that robustly aligns Large Language Models (LLMs) to multiple human objectives (e.g., instruction-following, helpfulness, safety) by maximizing the…

Machine Learning · Computer Science 2026-02-17 Seongho Son , William Bankes , Sangwoong Yoon , Shyam Sundhar Ramesh , Xiaohang Tang , Ilija Bogunovic

The importance of Reinforcement Learning from Human Feedback (RLHF) in aligning large language models (LLMs) with human values cannot be overstated. RLHF is a three-stage process that includes supervised fine-tuning (SFT), reward learning,…

Machine Learning · Computer Science 2025-05-27 Mudit Gaur , Amrit Singh Bedi , Raghu Pasupathy , Vaneet Aggarwal

The alignment of large language models (LLMs) aims to ensure their outputs adhere to human values, ethical standards, and legal norms. Traditional alignment methods often rely on resource-intensive fine-tuning (FT), which may suffer from…

Computation and Language · Computer Science 2025-09-11 Birong Pan , Yongqi Li , Weiyu Zhang , Wenpeng Lu , Mayi Xu , Shen Zhou , Yuanyuan Zhu , Ming Zhong , Tieyun Qian

Consider a two-player zero-sum stochastic game where the transition function can be embedded in a given feature space. We propose a two-player Q-learning algorithm for approximating the Nash equilibrium strategy via sampling. The algorithm…

Machine Learning · Computer Science 2019-06-04 Zeyu Jia , Lin F. Yang , Mengdi Wang

Reinforcement Learning from Human Feedback (RLHF) aligns language models to human preferences by employing a singular reward model derived from preference data. However, such an approach overlooks the rich diversity of human preferences…

Computation and Language · Computer Science 2024-12-30 Souradip Chakraborty , Jiahao Qiu , Hui Yuan , Alec Koppel , Furong Huang , Dinesh Manocha , Amrit Singh Bedi , Mengdi Wang

We study the global convergence of policy optimization for finding the Nash equilibria (NE) in zero-sum linear quadratic (LQ) games. To this end, we first investigate the landscape of LQ games, viewing it as a nonconvex-nonconcave…

Machine Learning · Computer Science 2021-02-12 Kaiqing Zhang , Zhuoran Yang , Tamer Başar

Large language models (LLMs) have shown tremendous success in following user instructions and generating helpful responses. Nevertheless, their robustness is still far from optimal, as they may generate significantly inconsistent responses…

Computation and Language · Computer Science 2024-03-25 Yukun Zhao , Lingyong Yan , Weiwei Sun , Guoliang Xing , Shuaiqiang Wang , Chong Meng , Zhicong Cheng , Zhaochun Ren , Dawei Yin

Learning problems commonly exhibit an interesting feedback mechanism wherein the population data reacts to competing decision makers' actions. This paper formulates a new game theoretic framework for this phenomenon, called "multi-player…

Computer Science and Game Theory · Computer Science 2022-04-08 Adhyyan Narang , Evan Faulkner , Dmitriy Drusvyatskiy , Maryam Fazel , Lillian J. Ratliff

The prevailing approach to aligning Large Language Models (LLMs) typically relies on human or AI feedback and assumes access to specific types of preference datasets. In our work, we question the efficacy of such datasets and explore…

Machine Learning · Computer Science 2024-03-19 Hao Sun

Mainstream approaches to aligning large language models (LLMs) heavily rely on human preference data, particularly when models require periodic updates. The standard process for iterative alignment of LLMs involves collecting new human…

Computation and Language · Computer Science 2024-10-01 Chen Zhang , Chengguang Tang , Dading Chong , Ke Shi , Guohua Tang , Feng Jiang , Haizhou Li

We introduce Stackelberg Learning from Human Feedback (SLHF), a new framework for preference optimization. SLHF frames the alignment problem as a sequential-move game between two policies: a Leader, which commits to an action, and a…

Machine Learning · Computer Science 2025-12-19 Barna Pásztor , Thomas Kleine Buening , Andreas Krause

Generative artificial intelligence (Generative AI), and in particular Large Language Models (LLMs) have gained significant popularity among researchers and industrial communities, paving the way for integrating LLMs in different domains,…

Computer Science and Game Theory · Computer Science 2024-10-15 Alonso Silva