跳到正文
arXiv cs.AI· Dongjun Han, Mingyu Lee, Ikjin Lee·· 10 小时前AI 评分31

LLM 辅助多保真度贝叶斯优化:融合专家知识与数值数据

LLM-Assisted Multi-Fidelity Bayesian Optimization: Fusing Expert Knowledge with Numerical Data

AI 导读

研究者提出 LLM-Assisted MFBO,在传统多保真度贝叶斯优化模型中加入知识基:由 LLM 解读专家对低保真模型所省略物理的描述,判断两个设计中哪个需要更大的带符号残差修正,再用成对高斯过程将这些判断转化为知识基,并由高保真数据校准其贡献与符号。在锂离子电池设计问题上,该方法将传统 MFBO 的遗憾曲线下面积降低 61%。控制实验显示,决定搜索是否加速的是知识质量而非 LLM 的选择。

正文 · 原文

View PDF

Abstract:Multi-fidelity Bayesian optimization (MFBO) reduces engineering design cost by combining inexpensive low-fidelity (LF) models with a few accurate high-fidelity (HF) evaluations and sequentially selecting designs to evaluate. However, when HF data are scarce, the LF-HF discrepancy is difficult to learn from numerical data alone, especially when physics omitted in the LF model makes it design-dependent. Yet even without sufficient data, domain experts often know which physics the LF model omits and under which conditions its effect grows. Existing multi-fidelity (MF) models cannot use such qualitative knowledge directly, but large language models (LLMs) can interpret it and compare designs accordingly. The proposed LLM-Assisted MFBO adds a knowledge basis to the conventional MF model: from an expert description of the omitted physics, an LLM judges which of two designs requires the larger signed residual correction, and a pairwise Gaussian process converts these judgments into the basis. HF data calibrate its contribution and sign, so the knowledge is not trusted blindly. On a lithium-ion battery design problem, the proposed method reduced the regret area under the curve of conventional MFBO by 61%. Knowledge quality, rather than the choice of LLM, determined whether the search was accelerated, as shown by a controlled study that varied the two independently. A knowledge-level ablation further quantified the contribution of each knowledge statement. These results show that LLM-interpreted expert knowledge can complement numerical data as an information source in MFBO.
Comments: 35 pages, 8 figures, 3 tables
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computational Engineering, Finance, and Science (cs.CE)
ACM classes: I.2.6; G.1.6; J.6
Cite as: arXiv:2611.24377 [cs.LG]
  (or arXiv:2611.24377v1 [cs.LG] for this version)
  https://doi.org/10.48550/arXiv.2611.24377

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Dongjun Han [view email]
[v1] Wed, 18 Nov 2026 13:07:03 UTC (2,352 KB)

来源:arXiv cs.AI · arxiv.org