English
Related papers

Related papers: Alignment of large language models with constraine…

200 papers

Reinforcement learning from human feedback (RLHF) has emerged as an effective approach to aligning large language models (LLMs) to human preferences. RLHF contains three steps, i.e., human preference collecting, reward learning, and policy…

Computation and Language · Computer Science 2024-03-29 Hao Lang , Fei Huang , Yongbin Li

We study deterministic and stochastic primal-dual sub-gradient algorithms for distributed optimization of a separable objective function with global inequality constraints. In both algorithms, the norm of the Lagrangian multipliers are…

Optimization and Control · Mathematics 2017-06-20 Masoud Badiei Khuzani , Na Li

We study the problem of computing deterministic optimal policies for constrained Markov decision processes (MDPs) with continuous state and action spaces, which are widely encountered in constrained dynamical systems. Designing…

Artificial Intelligence · Computer Science 2025-04-07 Sergio Rozada , Dongsheng Ding , Antonio G. Marques , Alejandro Ribeiro

Large Language models (LLMs) have shown promise as generators of symbolic control policies, producing interpretable program-like representations through iterative search. However, these models are not capable of separating the functional…

Machine Learning · Computer Science 2025-10-02 Carlo Bosio , Matteo Guarrera , Alberto Sangiovanni-Vincentelli , Mark W. Mueller

We introduce ALaRM, the first framework modeling hierarchical rewards in reinforcement learning from human feedback (RLHF), which is designed to enhance the alignment of large language models (LLMs) with human preferences. The framework…

Computation and Language · Computer Science 2024-03-19 Yuhang Lai , Siyuan Wang , Shujun Liu , Xuanjing Huang , Zhongyu Wei

Large language models (LLMs) are currently aligned using techniques such as reinforcement learning from human feedback (RLHF). However, these methods use scalar rewards that can only reflect user preferences on average. Pluralistic…

Computation and Language · Computer Science 2025-08-13 Jadie Adams , Brian Hu , Emily Veenhuis , David Joy , Bharadwaj Ravichandran , Aaron Bray , Anthony Hoogs , Arslan Basharat

Non-convex functional constrained optimization problems have gained substantial attention in machine learning and data science, addressing broad requirements that typically go beyond the often performance-centric objectives. An influential…

Optimization and Control · Mathematics 2025-10-29 Sang Bin Moon , Jong Gwang Kim , Ashish Chandra , Christopher Brinton , Abolfazl Hashemi

We study estimation and statistical inference for reward models used in aligning large language models (LLMs). A key component of LLM alignment is reinforcement learning from human feedback (RLHF), where humans compare pairs of…

Machine Learning · Statistics 2025-12-04 Pangpang Liu , Junwei Lu , Will Wei Sun

Reinforcement Learning from Human Feedback (RLHF) is a key method for aligning large language models (LLMs) with human preferences. However, current offline alignment approaches like DPO, IPO, and SLiC rely heavily on fixed preference…

Machine Learning · Computer Science 2024-06-25 Mucong Ding , Souradip Chakraborty , Vibhu Agrawal , Zora Che , Alec Koppel , Mengdi Wang , Amrit Bedi , Furong Huang

Fine-tuning Large Language Models (LLMs) incurs considerable training costs, driving the need for data-efficient training with optimised data ordering. Human-inspired strategies offer a solution by organising data based on human learning…

Computation and Language · Computer Science 2024-11-06 Yushi Yang , Andrew M. Bean , Robert McCraith , Adam Mahdi

Large Language Models (LLMs) have made significant strides in the field of artificial intelligence, showcasing their ability to interact with humans and influence human cognition through information dissemination. However, recent studies…

Computation and Language · Computer Science 2024-11-25 Qingquan Zhang , Qiqi Duan , Bo Yuan , Yuhui Shi , Jialin Liu

Large Language Models (LLMs) have shown remarkable performance in various natural language processing tasks but face challenges in mathematical reasoning, where complex problem-solving requires both linguistic understanding and mathematical…

Computation and Language · Computer Science 2025-03-20 Shuguang Chen , Guang Lin

A large number of objectives have been proposed to train latent variable generative models. We show that many of them are Lagrangian dual functions of the same primal optimization problem. The primal problem optimizes the mutual information…

Machine Learning · Statistics 2018-07-10 Shengjia Zhao , Jiaming Song , Stefano Ermon

Reinforcement Learning from Human Feedback (RLHF) is the standard method to align Large Language Models (LLMs) with human preferences. In this work, we introduce alignment tampering, a potential vulnerability where the LLM undergoing…

Artificial Intelligence · Computer Science 2026-05-27 Dongyoon Hahm , Dylan Hadfield-Menell , Kimin Lee

With the rapid development of Large Language Models (LLMs), LLM-based agents have been widely adopted in various fields, becoming essential for autonomous decision-making and interactive tasks. However, current work typically relies on…

Artificial Intelligence · Computer Science 2026-02-25 Shangheng Du , Jiabao Zhao , Jinxin Shi , Zhentao Xie , Xin Jiang , Yanhong Bai , Liang He

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

Stochastic gradient methods (SGMs) have been widely used for solving stochastic optimization problems. A majority of existing works assume no constraints or easy-to-project constraints. In this paper, we consider convex stochastic…

Optimization and Control · Mathematics 2022-01-03 Yonggui Yan , Yangyang Xu

Generating long, coherent text remains a challenge for large language models (LLMs), as they lack hierarchical planning and structured organization in discourse generation. We introduce Structural Alignment, a novel method that aligns LLMs…

Computation and Language · Computer Science 2026-02-04 Zae Myung Kim , Anand Ramachandran , Farideh Tavazoee , Joo-Kyung Kim , Oleg Rokhlenko , Dongyeop Kang

Large language models (LLMs) exhibit remarkable capabilities across diverse tasks, yet aligning them efficiently and effectively with human expectations remains a critical challenge. This thesis advances LLM alignment by introducing novel…

Computation and Language · Computer Science 2025-06-12 Yuxin Jiang

In this work, we revisit a classical incremental implementation of the primal-descent dual-ascent gradient method used for the solution of equality constrained optimization problems. We provide a short proof that establishes the linear…

Optimization and Control · Mathematics 2020-01-17 Sulaiman A. Alghunaim , Ali H. Sayed
‹ Prev 1 3 4 5 6 7 10 Next ›