English
Related papers

Related papers: Certifiable Safe RLHF: Fixed-Penalty Constraint Op…

200 papers

Large language models (LLMs) need reliable test-time control of hallucinations. Existing conformal methods for LLMs typically provide only \emph{marginal} guarantees and rely on a single global threshold, which can under-cover hard prompts,…

Machine Learning · Computer Science 2026-03-31 Kai Ye , Qingtao Pan , Shuo Li

High-level penetration of intermittent renewable energy sources (RESs) has introduced significant uncertainties into modern power systems. In order to rapidly and economically respond to the fluctuations of power system operating state,…

Systems and Control · Electrical Eng. & Systems 2023-08-08 Pengfei Wu , Chen Chen , Dexiang Lai , Jian Zhong

While Reinforcement Learning from Human Feedback (RLHF) effectively aligns pretrained Large Language and Vision-Language Models (LLMs, and VLMs) with human preferences, its computational cost and complexity hamper its wider adoption. To…

The problem of safely learning and controlling a dynamical system - i.e., of stabilizing an originally (partially) unknown system while ensuring that it does not leave a prescribed 'safe set' - has recently received tremendous attention in…

Systems and Control · Electrical Eng. & Systems 2023-10-10 Jafar Abbaszadeh Chekan , Cedric Langbort

Reinforcement Learning with Verifiable Rewards~(RLVR) has emerged as a powerful learn-to-reason paradigm for large reasoning models to tackle complex tasks. However, the current RLVR paradigm is still not efficient enough, as it works in a…

Computation and Language · Computer Science 2026-03-10 Junjie Zhang , Guozheng Ma , Shunyu Liu , Haoyu Wang , Jiaxing Huang , Ting-En Lin , Fei Huang , Yongbin Li , Dacheng Tao

The emergence of LM-based judging reward modeling, represented by generative reward models, has successfully made reinforcement learning from AI feedback (RLAIF) efficient and scalable. To further advance this paradigm, we propose a core…

Computation and Language · Computer Science 2025-11-18 Meiling Ning , Zhongbao Zhang , Junda Ye , Jiabao Guo , Qingyuan Guan

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

Different classes of safe reinforcement learning algorithms have shown satisfactory performance in various types of safety requirement scenarios. However, the existing methods mainly address one or several classes of specific safety…

Machine Learning · Computer Science 2024-07-09 Zepeng Wang , Chao Ma , Linjiang Zhou , Libing Wu , Lei Yang , Xiaochuan Shi , Guojun Peng

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

In recent advancements in Conversational Large Language Models (LLMs), a concerning trend has emerged, showing that many new base LLMs experience a knowledge reduction in their foundational capabilities following Supervised Fine-Tuning…

Computation and Language · Computer Science 2024-03-06 Chen Zheng , Ke Sun , Hang Wu , Chenguang Xi , Xun Zhou

Recent advances in alignment techniques such as Supervised Fine-Tuning (SFT), Reinforcement Learning from Human Feedback (RLHF), and Direct Preference Optimization (DPO) have improved the safety of large language models (LLMs). However,…

Computation and Language · Computer Science 2026-02-26 Mengxuan Hu , Vivek V. Datla , Anoop Kumar , Zihan Guan , Sheng Li , Alfy Samuel , Daben Liu

We introduce a novel approach to large language model (LLM) distillation by formulating it as a constrained reinforcement learning problem. While recent work has begun exploring the integration of task-specific rewards into distillation…

Machine Learning · Computer Science 2025-09-30 Matthieu Zimmer , Xiaotong Ji , Tu Nguyen , Haitham Bou Ammar

Reinforcement learning (RL) has proven to be particularly effective in solving complex decision-making problems for a wide range of applications. Safe reinforcement learning refers to a class of constrained problems where the constraint…

Systems and Control · Electrical Eng. & Systems 2026-05-13 Dhruv Singh Kushwaha , Zoleikha Abdollahi Biron

Recent advances in large language models (LLMs) have demonstrated significant progress in performing complex tasks. While Reinforcement Learning from Human Feedback (RLHF) has been effective in aligning LLMs with human preferences, it is…

Machine Learning · Computer Science 2025-05-30 Chaoqi Wang , Zhuokai Zhao , Yibo Jiang , Zhaorun Chen , Chen Zhu , Yuxin Chen , Jiayi Liu , Lizhu Zhang , Xiangjun Fan , Hao Ma , Sinong Wang

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

Large language models (LLMs) are trained on a deluge of text data with limited quality control. As a result, LLMs can exhibit unintended or even harmful behaviours, such as leaking information, fake news or hate speech. Countermeasures,…

Machine Learning · Computer Science 2024-08-05 Jingtong Su , Julia Kempe , Karen Ullrich

Practical reinforcement learning problems are often formulated as constrained Markov decision process (CMDP) problems, in which the agent has to maximize the expected return while satisfying a set of prescribed safety constraints. In this…

Machine Learning · Computer Science 2019-09-23 Shin-ichi Maeda , Hayato Watahiki , Shintarou Okada , Masanori Koyama

Reinforcement Learning from Human Feedback (RLHF) is a pivotal technique for aligning large language models (LLMs) with human preferences, yet it is susceptible to reward overoptimization, in which policy models overfit to the reward model,…

The ability to rigorously estimate the failure rates of large language models (LLMs) is a prerequisite for their safe deployment. Currently, however, practitioners often face a tradeoff between expensive human gold standards and potentially…

Computation and Language · Computer Science 2026-04-07 Minghe Shen , Ananth Balashankar , Adam Fisch , David Madras , Miguel Rodrigues

Safe reinforcement learning (RL) agents accomplish given tasks while adhering to specific constraints. Employing constraints expressed via easily-understandable human language offers considerable potential for real-world applications due to…

Machine Learning · Computer Science 2024-05-16 Xingzhou Lou , Junge Zhang , Ziyan Wang , Kaiqi Huang , Yali Du