English
Related papers

Related papers: HIPO: Instruction Hierarchy via Constrained Reinfo…

200 papers

We present a novel unified bilevel optimization-based framework, \textsf{PARL}, formulated to address the recently highlighted critical issue of policy alignment in reinforcement learning using utility or preference-based feedback. We…

Machine Learning · Computer Science 2024-05-02 Souradip Chakraborty , Amrit Singh Bedi , Alec Koppel , Dinesh Manocha , Huazheng Wang , Mengdi Wang , Furong Huang

We propose a hierarchical architecture for efficiently computing high-quality solutions to structured mixed-integer programs (MIPs). To reduce computational effort, our approach decouples the original problem into a higher level problem and…

Optimization and Control · Mathematics 2025-12-04 Stefan Clarke , Bartolomeo Stellato

We introduce a problem-level prioritization framework for RL post-training of large language models. Building on insights from prioritized replay in deep RL, as well as prior observations that rollouts with intermediate success rates tend…

Machine Learning · Computer Science 2026-01-07 Mehdi Fatemi

The prevalent deployment of learning from human preferences through reinforcement learning (RLHF) relies on two important approximations: the first assumes that pairwise preferences can be substituted with pointwise rewards. The second…

Artificial Intelligence · Computer Science 2023-11-23 Mohammad Gheshlaghi Azar , Mark Rowland , Bilal Piot , Daniel Guo , Daniele Calandriello , Michal Valko , Rémi Munos

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

Legged locomotion is a challenging task for learning algorithms, especially when the task requires a diverse set of primitive behaviors. To solve these problems, we introduce a hierarchical framework to automatically decompose complex…

Machine Learning · Computer Science 2019-05-23 Deepali Jain , Atil Iscen , Ken Caluwaerts

Large Language Models (LLMs) generate functionally correct solutions but often fall short in code efficiency, a critical bottleneck for real-world deployment. In this paper, we introduce a novel test-time iterative optimization framework to…

Software Engineering · Computer Science 2025-06-04 Mingzhe Du , Luu Anh Tuan , Yue Liu , Yuhao Qing , Dong Huang , Xinyi He , Qian Liu , Zejun Ma , See-kiong Ng

Reinforcement Learning from Human Feedback (RLHF) has become a pivotal paradigm in artificial intelligence to align large models with human preferences. In this paper, we propose a novel statistical framework to simultaneously conduct the…

Machine Learning · Statistics 2026-05-01 Nan Lu , Ethan Lee , Ethan X. Fang , Junwei Lu

Reinforcement learning from human feedback (RLHF) is a crucial technique in aligning large language models (LLMs) with human preferences, ensuring these LLMs behave in beneficial and comprehensible ways to users. However, a longstanding…

Artificial Intelligence · Computer Science 2024-03-27 Feiteng Fang , Liang Zhu , Min Yang , Xi Feng , Jinchang Hou , Qixuan Zhao , Chengming Li , Xiping Hu , Ruifeng Xu

Large language models (LLMs) trained via pretraining and supervised fine-tuning (SFT) can still produce harmful and misaligned outputs, or struggle in domains like math and coding. Reinforcement learning (RL)-based post-training methods,…

Computation and Language · Computer Science 2026-05-19 Zhichao Wang , Kiran Ramnath , Bin Bi , Shiva Kumar Pentyala , Sougata Chaudhuri , Shubham Mehrotra , Zixu , Zhu , Xiang-Bo Mao , Sitaram Asur , Na , Cheng

Large Language Models (LLMs) are increasingly deployed in agentic and retrieval-augmented generation (RAG) systems, where they must execute user-specified tasks over externally provided reference text. In practice, such context is often…

Artificial Intelligence · Computer Science 2026-05-29 Zeli Su , Zhankai Xu , Tianlei Chen , Longfei Zheng , Xiaolu Zhang , Jun Zhou , Wentao Zhang

Large language models (LLMs) often contain misleading content, emphasizing the need to align them with human values to ensure secure AI systems. Reinforcement learning from human feedback (RLHF) has been employed to achieve this alignment.…

Computation and Language · Computer Science 2024-02-28 Feifan Song , Bowen Yu , Minghao Li , Haiyang Yu , Fei Huang , Yongbin Li , Houfeng Wang

Existing research on instruction following largely focuses on tasks with simple instructions and short responses. In this work, we explore multi-constraint instruction following for generating long-form text. We create Suri, a dataset with…

Computation and Language · Computer Science 2024-10-03 Chau Minh Pham , Simeng Sun , Mohit Iyyer

As large language models increasingly drive real-world applications, aligning them with human values becomes paramount. Reinforcement Learning from Human Feedback (RLHF) has emerged as a key technique, translating preference data into…

Machine Learning · Computer Science 2025-02-07 Yunzhen Feng , Ariel Kwiatkowski , Kunhao Zheng , Julia Kempe , Yaqi Duan

Large Language Models (LLMs) often generate substantively relevant content but fail to adhere to formal constraints, leading to outputs that are conceptually correct but procedurally flawed. Traditional prompt refinement approaches focus on…

Artificial Intelligence · Computer Science 2026-01-08 Alberto Purpura , Li Wang , Sahil Badyal , Eugenio Beaufrand , Adam Faulkner

Reinforcement Learning from Human Feedback (RLHF) is crucial for aligning Large Language Models (LLMs) with human values. However, RLHF has been continuously challenged by its high complexity in implementation and computation consumption,…

Machine Learning · Computer Science 2026-03-24 Yuhao Du , Zhuo Li , Pengyu Cheng , Zhihong Chen , Yuejiao Xie , Xiang Wan , Anningzhe Gao

Reinforcement learning is used to align language models with human preference signals after first pre-training the model to predict the next token of text within a large corpus using likelihood maximization. Before being deployed in a…

Computation and Language · Computer Science 2024-08-30 Alec Solway

While scaling the length of responses at test-time has been shown to markedly improve the reasoning abilities and performance of large language models (LLMs), it often results in verbose outputs and increases inference cost. Prior…

Computation and Language · Computer Science 2025-11-18 Chengyu Huang , Zhengxin Zhang , Claire Cardie

Preference learning algorithms (e.g., RLHF and DPO) are frequently used to steer LLMs to produce generations that are more preferred by humans, but our understanding of their inner workings is still limited. In this work, we study the…

Machine Learning · Computer Science 2024-11-01 Angelica Chen , Sadhika Malladi , Lily H. Zhang , Xinyi Chen , Qiuyi Zhang , Rajesh Ranganath , Kyunghyun Cho

Post-training of LLMs with RLHF, and subsequently preference optimization algorithms such as DPO, IPO, etc., made a big difference in improving human alignment. However, all such techniques can only work with a single (human) objective. In…

Machine Learning · Computer Science 2025-05-19 Akhil Agnihotri , Rahul Jain , Deepak Ramachandran , Zheng Wen