Improving LLM Performance Through Black-Box Online Tuning: A Case for Adding System Specs to Factsheets for Trusted AI

2026-03-11 · Yonas Atinafu, Henry Lin, Robin Cohen arxiv

In this paper, we present a novel black-box online controller that uses only end-to-end measurements over short segments, without internal instrumentation, and hill climbing to maximize goodput, defined as the throughput of requests that satisfy the service-level objective. We provide empirical evidence that this design is well-founded. Using this advance in LLM serving as a concrete example, we then discuss the importance of integrating system performance and sustainability metrics into Factsheets for organizations adopting AI systems.

📄 PDF Abstract BibTeX arXiv:2603.11340

Code (0)

등록된 구현이 없습니다.

Learning the Context of Errors: Black-Box Online Adaptation of Time Series Foundation Models

2026-06-12 · Xilin Dai, Yiding Liu, Hongjie Xia, Yifan Hu 외 arxiv

The rapid evolution of Time Series Foundation Models (TSFMs) has advanced zero-shot forecasting across diverse domains. Inspired by the current form of Large Language Models, future TSFMs may be offered as commercialized…

Meta-Learning for Physically-Constrained Neural System Identification

2025-01-10 · Ankush Chakrabarty, Gordon Wichern, Vedang M. Deshpande, Abraham P. Vinod 외

We present a gradient-based meta-learning framework for rapid adaptation of neural state-space models (NSSMs) for black-box system identification. When applicable, we also incorporate domain-specific physical constraints…

Indoor Localization Meta-Learning State Estimation State Space Models

Bayesian Optimization Parameter Tuning Framework for a Lyapunov Based Path Following Controller

2025-12-14 · Zhewen Zheng, Wenjing Cao, Hongkang Yu, Mo Chen 외 arxiv

Parameter tuning in real-world experiments is constrained by the limited evaluation budget available on hardware. The path-following controller studied in this paper reflects a typical situation in nonlinear geometric co…

Black-box Prompt Tuning with Subspace Learning

2023-05-04 · Yuanhang Zheng, Zhixing Tan, Peng Li, Yang Liu

Black-box prompt tuning employs derivative-free optimization algorithms to learn prompts within low-dimensional subspaces rather than back-propagating through the network of Large Language Models (LLMs). Recent studies r…

Meta-Learning

Variable Prioritization in Nonlinear Black Box Methods: A Genetic Association Case Study

2018-01-22 · Lorin Crawford, Seth R. Flaxman, Daniel E. Runcie, Mike West

The central aim in this paper is to address variable selection questions in nonlinear and nonparametric regression. Motivated by statistical genetics, where nonlinear interactions are of particular interest, we introduce…

regression Variable Selection