English
Related papers

Related papers: BEACON: Bayesian Optimal Stopping for Efficient LL…

200 papers

Recently, the increasing use of deep reinforcement learning for flow control problems has led to a new area of research, focused on the coupling and the adaptation of the existing algorithms to the control of numerical fluid dynamics…

Computational Physics · Physics 2024-04-19 Jonathan Viquerat , Philippe Meliga , Pablo Jeken , Elie Hachem

Multi-agent frameworks can substantially boost the reasoning power of large language models (LLMs), but they typically incur heavy computational costs and lack convergence guarantees. To overcome these challenges, we recast multi-LLM…

Machine Learning · Computer Science 2025-06-11 Xie Yi , Zhanke Zhou , Chentao Cao , Qiyu Niu , Tongliang Liu , Bo Han

We develop the first Bayesian Optimization algorithm, BLOSSOM, which selects between multiple alternative acquisition functions and traditional local optimization at each step. This is combined with a novel stopping condition based on…

Machine Learning · Statistics 2018-05-23 Mark McLeod , Michael A. Osborne , Stephen J. Roberts

Chain-of-Thought (CoT) reasoning has driven recent gains of large language models (LLMs) on reasoning-intensive tasks by externalizing intermediate steps. However, excessive or redundant reasoning -- so-called overthinking -- can increase…

Computation and Language · Computer Science 2025-10-14 Renliang Sun , Wei Cheng , Dawei Li , Haifeng Chen , Wei Wang

Bayesian optimization is a popular framework for efficiently tackling black-box search problems. As a rule, these algorithms operate by iteratively choosing what to evaluate next until some predefined budget has been exhausted. We…

Machine Learning · Statistics 2024-12-12 James T. Wilson

RANSAC-based algorithms are the standard techniques for robust estimation in computer vision. These algorithms are iterative and computationally expensive; they alternate between random sampling of data, computing hypotheses, and running…

Computer Vision and Pattern Recognition · Computer Science 2023-09-27 Valter Piedade , Pedro Miraldo

Bayesian optimization (BO) provides a powerful framework for optimizing black-box, expensive-to-evaluate functions. It is therefore an attractive tool for engineering design problems, typically involving multiple objectives. Thanks to the…

Machine Learning · Computer Science 2024-09-06 Navid Ansari , Alireza Javanmardi , Eyke Hüllermeier , Hans-Peter Seidel , Vahid Babaei

Carefully engineered system prompts play a critical role in guiding the behavior of LLM agents, but their considerable length introduces significant drawbacks, including increased inference latency, higher computational cost, and reduced…

Computation and Language · Computer Science 2025-12-01 Jiancheng Dong , Pengyue Jia , Jingyu Peng , Maolin Wang , Yuhao Wang , Lixin Su , Xin Sun , Shuaiqiang Wang , Dawei Yin , Xiangyu Zhao

We develop a new computational approach for "focused" optimal Bayesian experimental design with nonlinear models, with the goal of maximizing expected information gain in targeted subsets of model parameters. Our approach considers…

Computation · Statistics 2019-03-28 Chi Feng , Youssef M. Marzouk

Bayesian Deep Ensembles (BDEs) represent a powerful approach for uncertainty quantification in deep learning, combining the robustness of Deep Ensembles (DEs) with flexible multi-chain MCMC. While DEs are affordable in most deep learning…

Machine Learning · Computer Science 2026-04-21 Emanuel Sommer , Rickmer Schulte , Sarah Deubner , Julius Kobialka , David Rügamer

In this paper, Bayesian quickest change detection problems with sampling right constraints are considered. Specifically, there is a sequence of random variables whose probability density function will change at an unknown time. The goal is…

Information Theory · Computer Science 2014-07-16 Jun Geng , Erhan Bayraktar , Lifeng Lai

In neural text generation such as neural machine translation, summarization, and image captioning, beam search is widely used to improve the output text quality. However, in the neural generation setting, hypotheses can finish in different…

Computation and Language · Computer Science 2018-09-05 Liang Huang , Kai Zhao , Mingbo Ma

The high cost and data scarcity in scientific exploration have motivated the use of large language models (LLMs) as knowledge-driven components in Bayesian optimization (BO). However, existing approaches typically embed LLMs directly into…

We propose a new model to assess the mastery level of a given skill efficiently. The model, called Bayesian Adaptive Mastery Assessment (BAMA), uses information on the accuracy and the response time of the answers given and infers the…

Optimization and Control · Mathematics 2021-03-08 Anni Sapountzi , Sandjai Bhulai , Ilja Cornelisz , Chris van Klaveren

We obtain a reliability acceptance sampling plan for independent competing risk data under interval censoring schemes using the Bayesian approach. At first, the Bayesian reliability acceptance sampling plan is obtained where the decision…

Applications · Statistics 2025-10-21 Biswabrata Pradhan , Rathin Das

Large language models (LLMs) are often queried multiple times at test time, with predictions aggregated by majority vote. While effective, this self-consistency strategy (arXiv:2203.11171) requires a fixed number of calls and can fail when…

Computation and Language · Computer Science 2025-11-05 Ehsan Aghazadeh , Ahmad Ghasemi , Hedyeh Beyhaghi , Hossein Pishro-Nik

This paper addresses the challenges of efficiently fine-tuning large language models (LLMs) by exploring data efficiency and hyperparameter optimization. We investigate the minimum data required for effective fine-tuning and propose a novel…

Computation and Language · Computer Science 2024-07-22 Michael Oliver , Guan Wang

We introduce a simple, yet novel entropy-based framework to drive token efficiency in large language models during reasoning tasks. Our approach uses Shannon entropy from token-level logprobs as a confidence signal to enable early stopping,…

Machine Learning · Computer Science 2025-10-29 Aman Sharma , Paras Chopra

Large Language Models (LLMs) increasingly rely on multi-turn reasoning and interaction, such as adaptive retrieval-augmented generation (RAG) and ReAct-style agents, to answer difficult questions. These methods improve accuracy by…

Computation and Language · Computer Science 2026-04-07 Xiaofan Zhou , Huy Nguyen , Bo Yu , Chenxi Liu , Lu Cheng

Alignment has greatly improved large language models (LLMs)' output quality at the cost of diversity, yielding highly similar outputs across generations. We propose Base-Aligned Model Collaboration (BACo), an inference-time token-level…

Computation and Language · Computer Science 2025-11-11 Yichen Wang , Chenghao Yang , Tenghao Huang , Muhao Chen , Jonathan May , Mina Lee