English
Related papers

Related papers: Optimal Policy Minimum Bayesian Risk

200 papers

Large language models (LLMs) are often equipped with multi-sample decoding strategies. An LLM implicitly defines an arithmetic code book, facilitating efficient and embarrassingly parallelizable \textbf{arithmetic sampling} to produce…

Artificial Intelligence · Computer Science 2025-04-29 Aditya Parashar , Aditya Vikram Singh , Avinash Amballa , Jinlin Lai , Benjamin Rozonoyer

Training models to effectively use test-time compute is crucial for improving the reasoning performance of LLMs. Current methods mostly do so via fine-tuning on search traces or running RL with 0/1 outcome reward, but do these approaches…

The performance gains of LLMs have historically been driven by scaling up model size and training data. However, the rapidly diminishing availability of high-quality training data is introducing a fundamental bottleneck, shifting the focus…

Computation and Language · Computer Science 2025-10-14 Zhichao Wang , Cheng Wan , Dong Nie

The availability of large pre-trained models is changing the landscape of Machine Learning research and practice, moving from a training-from-scratch to a fine-tuning paradigm. While in some applications the goal is to "nudge" the…

Machine Learning · Computer Science 2022-11-15 Tomasz Korbak , Hady Elsahar , Germán Kruszewski , Marc Dymetman

Recently, scaling test-time compute on Large Language Models (LLM) has garnered wide attention. However, there has been limited investigation of how various reasoning prompting strategies perform as scaling. In this paper, we focus on a…

Artificial Intelligence · Computer Science 2025-08-18 Yexiang Liu , Zekun Li , Zhi Fang , Nan Xu , Ran He , Tieniu Tan

Model-based reinforcement learning (RL) can be effectively supported at scale through the use of world models. However, in practice, scaling such approaches remains fundamentally limited. A commonly recognized challenge is model bias and…

Machine Learning · Computer Science 2026-05-27 Xiaoyuan Cheng , Wenxuan Yuan , Zhancun Mu , Yuanzhao Zhang , Yiming Yang , Hai Wang , Zhuo Sun , Che Liu

Bayesian Neural Networks (BNNs) are trained to optimize an entire distribution over their weights instead of a single set, having significant advantages in terms of, e.g., interpretability, multi-task learning, and calibration. Because of…

Machine Learning · Computer Science 2022-10-07 Jary Pomponi , Simone Scardapane , Aurelio Uncini

Minimum Bayes-risk (MBR) decoding has recently gained renewed attention in text generation. MBR decoding considers texts sampled from a model as pseudo-references and selects the text with the highest similarity to the others. Therefore,…

Computation and Language · Computer Science 2024-04-02 Atsumoto Ohashi , Ukyo Honda , Tetsuro Morimura , Yuu Jinnai

Recent advances in large language models (LLMs) have increasingly relied on reinforcement learning (RL) to improve their reasoning capabilities. Three types of approaches have been widely adopted: The first relies on a deep neural network…

Machine Learning · Computer Science 2026-05-19 Shijin Gong , Kai Ye , Jin Zhu , Xinyu Zhang , Hongyi Zhou , Chengchun Shi

Standard reinforcement learning (RL) aims to find an optimal policy that identifies the best action for each state. However, in healthcare settings, many actions may be near-equivalent with respect to the reward (e.g., survival). We…

Machine Learning · Computer Science 2020-07-27 Shengpu Tang , Aditya Modi , Michael W. Sjoding , Jenna Wiens

Driven by recent advances in artificial intelligence (AI), a growing literature has demonstrated the potential for using large language models (LLMs) as scalable surrogates to generate human-like responses in many business applications. Two…

Machine Learning · Computer Science 2025-12-30 Lei Wang , Zikun Ye , Jinglong Zhao

Offline model-based reinforcement learning (MBRL) serves as a competitive framework that can learn well-performing policies solely from pre-collected data with the help of learned dynamics models. To fully unleash the power of offline MBRL,…

Machine Learning · Computer Science 2025-02-18 Yu-Wei Yang , Yun-Ming Chan , Wei Hung , Xi Liu , Ping-Chun Hsieh

Linear Temporal Logic (LTL) is widely used to specify high-level objectives for system policies, and it is highly desirable for autonomous systems to learn the optimal policy with respect to such specifications. However, learning the…

Machine Learning · Computer Science 2023-10-26 Daqian Shao , Marta Kwiatkowska

Predictive models often need to work with incomplete information in real-world tasks. Consequently, they must provide reliable probability or confidence estimation, especially in large-scale decision-making and planning tasks. Current large…

Computation and Language · Computer Science 2025-10-22 Yu Feng , Ben Zhou , Weidong Lin , Dan Roth

We propose policy gradient algorithms for solving a risk-sensitive reinforcement learning (RL) problem in on-policy as well as off-policy settings. We consider episodic Markov decision processes, and model the risk using the broad class of…

Machine Learning · Computer Science 2024-06-25 Nithia Vijayan , Prashanth L. A

Training Large Language Models (LLMs) for chain-of-thought reasoning presents a significant challenge: supervised fine-tuning on a single "golden" rationale hurts generalization as it penalizes equally valid alternatives, whereas…

Computation and Language · Computer Science 2025-11-14 Mingye Zhu , Yi Liu , Zheren Fu , Quan Wang , Yongdong Zhang

Reward models (RMs) play a critical role in enhancing the reasoning performance of LLMs. For example, they can provide training signals to finetune LLMs during reinforcement learning (RL) and help select the best answer from multiple…

Computation and Language · Computer Science 2025-10-06 Qiyuan Liu , Hao Xu , Xuhong Chen , Wei Chen , Yee Whye Teh , Ning Miao

Reinforcement learning algorithms are typically designed for discrete-time dynamics, even though the underlying real-world control systems are often continuous in time. In this paper, we study the problem of continuous-time reinforcement…

Machine Learning · Computer Science 2026-03-03 Klemens Iten , Lenart Treven , Bhavya Sukhija , Florian Dörfler , Andreas Krause

Learned representations in deep reinforcement learning (DRL) have to extract task-relevant information from complex observations, balancing between robustness to distraction and informativeness to the policy. Such stable and rich…

Machine Learning · Computer Science 2021-10-28 Mete Kemertas , Tristan Aumentado-Armstrong

Reward-based alignment methods for large language models (LLMs) face two key limitations: vulnerability to reward hacking, where models exploit flaws in the reward signal; and reliance on brittle, labor-intensive prompt engineering when…

Computation and Language · Computer Science 2025-05-20 Zae Myung Kim , Chanwoo Park , Vipul Raheja , Suin Kim , Dongyeop Kang
‹ Prev 1 3 4 5 6 7 10 Next ›