English
Related papers

Related papers: Weak-to-Strong Elicitation via Mismatched Wrong Dr…

200 papers

Large language models (LLMs) are increasingly adapted to downstream tasks via reinforcement learning (RL) methods like Group Relative Policy Optimization (GRPO), which often require thousands of rollouts to learn new tasks. We argue that…

Reinforcement Learning (RL) has emerged as a central paradigm for advancing Large Language Models (LLMs), where pre-training and RL post-training share the same log-likelihood formulation. In contrast, recent RL approaches for diffusion…

Machine Learning · Computer Science 2025-09-30 Shuchen Xue , Chongjian Ge , Shilong Zhang , Yichen Li , Zhi-Ming Ma

Enhancing the mathematical reasoning of Large Language Models (LLMs) is a pivotal challenge in advancing AI capabilities. While Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) are the dominant training paradigms, a systematic…

Machine Learning · Computer Science 2025-07-14 Hiroshi Yoshihara , Taiki Yamaguchi , Yuichi Inoue

We consider an improper reinforcement learning setting where a learner is given $M$ base controllers for an unknown Markov decision process, and wishes to combine them optimally to produce a potentially new controller that can outperform…

Machine Learning · Computer Science 2021-07-06 Mohammadi Zaki , Avinash Mohan , Aditya Gopalan , Shie Mannor

A novel gradient boosting framework is proposed where shallow neural networks are employed as ``weak learners''. General loss functions are considered under this unified framework with specific examples presented for classification,…

Machine Learning · Computer Science 2020-06-16 Sarkhan Badirli , Xuanqing Liu , Zhengming Xing , Avradeep Bhowmik , Khoa Doan , Sathiya S. Keerthi

This paper investigates energy guidance in generative modeling, where the target distribution is defined as $q(\mathbf x) \propto p(\mathbf x)\exp(-\beta \mathcal E(\mathbf x))$, with $p(\mathbf x)$ being the data distribution and $\mathcal…

Machine Learning · Computer Science 2025-03-10 Shiyuan Zhang , Weitong Zhang , Quanquan Gu

Large language models (LLMs), such as GPT-4, have shown remarkable performance in natural language processing (NLP) tasks, including challenging mathematical reasoning. However, most existing open-source models are only pre-trained on…

Computation and Language · Computer Science 2025-06-05 Haipeng Luo , Qingfeng Sun , Can Xu , Pu Zhao , Jianguang Lou , Chongyang Tao , Xiubo Geng , Qingwei Lin , Shifeng Chen , Yansong Tang , Dongmei Zhang

We present Future-KL Influenced Policy Optimization (FIPO), a reinforcement learning algorithm designed to overcome reasoning bottlenecks in large language models. While GRPO style training scales effectively, it typically relies on…

Machine Learning · Computer Science 2026-04-01 Chiyu Ma , Shuo Yang , Kexin Huang , Jinda Lu , Haoming Meng , Shangshang Wang , Bolin Ding , Soroush Vosoughi , Guoyin Wang , Jingren Zhou

Large language models (LLMs) are increasingly applied to complex reasoning tasks that require executing several complex steps before receiving any reward. Properly assigning credit to these steps is essential for enhancing model…

Supervised Fine-Tuning (SFT) has been a go-to and effective method for enhancing long chain-of-thought (CoT) reasoning in relatively small LLMs by fine-tuning them with long CoT responses from larger LLMs. To continually improve reasoning…

Machine Learning · Computer Science 2025-02-20 Wang Yang , Hongye Jin , Jingfeng Yang , Vipin Chaudhary , Xiaotian Han

Off-policy model-free deep reinforcement learning methods using previously collected data can improve sample efficiency over on-policy policy gradient techniques. On the other hand, on-policy algorithms are often more stable and easier to…

Machine Learning · Computer Science 2017-06-02 Shixiang Gu , Timothy Lillicrap , Zoubin Ghahramani , Richard E. Turner , Bernhard Schölkopf , Sergey Levine

Model-based reinforcement learning methods learn a dynamics model with real data sampled from the environment and leverage it to generate simulated data to derive an agent. However, due to the potential distribution mismatch between…

Machine Learning · Computer Science 2020-10-29 Jian Shen , Han Zhao , Weinan Zhang , Yong Yu

Recent advances in large reasoning models (LRMs) demonstrate that sophisticated behaviors such as multi-step reasoning and self-reflection can emerge via reinforcement learning with verifiable rewards~(\textit{RLVR}). However, existing…

Machine Learning · Computer Science 2025-06-24 Jianhao Yan , Yafu Li , Zican Hu , Zhi Wang , Ganqu Cui , Xiaoye Qu , Yu Cheng , Yue Zhang

Achieving fast and stable off-policy learning in deep reinforcement learning (RL) is challenging. Most existing methods rely on semi-gradient temporal-difference (TD) methods for their simplicity and efficiency, but are consequently…

Machine Learning · Computer Science 2025-09-22 Esraa Elelimy , Brett Daley , Andrew Patterson , Marlos C. Machado , Adam White , Martha White

Pretrained language models have shown superior performance on many natural language processing tasks, yet they still struggle at multi-step formal reasoning tasks like grade school math problems. One key challenge of finetuning them to…

Machine Learning · Computer Science 2023-02-20 Ansong Ni , Jeevana Priya Inala , Chenglong Wang , Oleksandr Polozov , Christopher Meek , Dragomir Radev , Jianfeng Gao

We leverage embedding duplication between aligned sub-words to extend the Parent-Child transfer learning method, so as to improve low-resource machine translation. We conduct experiments on benchmark datasets of My-En, Id-En and Tr-En…

Computation and Language · Computer Science 2022-05-10 Minhan Xu , Yu Hong

Reinforcement learning (RL) is vital for optimizing large language models (LLMs). Recent Group Relative Policy Optimization (GRPO) estimates advantages using multiple on-policy outputs per prompt, leading to high computational costs and low…

Computation and Language · Computer Science 2025-06-12 Siheng Li , Zhanhui Zhou , Wai Lam , Chao Yang , Chaochao Lu

Lossless speculative decoding accelerates target large language model (LLM) inference by employing a lightweight draft model for generating tree-structured candidates, which are subsequently verified in parallel by the target LLM.…

Computation and Language · Computer Science 2024-08-29 Lujun Gui , Bin Xiao , Lei Su , Weipeng Chen

Recent progress in large language models (LLMs) highlights the power of scaling test-time compute to achieve strong performance on complex tasks, such as mathematical reasoning and code generation. This raises a critical question: how…

Machine Learning · Computer Science 2025-11-26 Feng Chen , Allan Raventos , Nan Cheng , Surya Ganguli , Shaul Druckmann

On-policy self-distillation, where a student is pulled toward a copy of itself conditioned on privileged context (e.g., a verified solution or feedback), offers a promising direction for advancing reasoning capability without a stronger…

Machine Learning · Computer Science 2026-05-13 Guobin Shen , Xiang Cheng , Chenxiao Zhao , Lei Huang , Jindong Li , Dongcheng Zhao , Xing Yu