【讲座主题】

Efficient Budget Allocation for Large-Scale LLM-Enabled Virtual Screening   

【时间】

2025-11-18 10:00    

【地点】

普陀校区理科大楼A614       

【主讲人】

范薇薇    

【主持人】

王天翔

【主办单位】

统计学院

【主讲人简介】

范薇薇，现为同济大学经济与管理学院副教授。博士毕业于香港科技大学工业工程与物流管理系，本科毕业于中国科学技术大学应用数学系。她的研究兴趣包括仿真优化、鲁棒优化，及其在医疗管理、供应链管理等方面的应用。在《Management Science》、《Operations Research》、《系统工程理论与实践》等国内外管理学权威期刊发表发多篇论文。主持国家自然科学基金委青年项目（B类）、面上项目、青年项目（C类）等。目前担任管理科学与工程学会服务科学与工程分会副秘书长，运筹学会随机服务分会和医疗运作管理分会、“双法” 研究会服务科学与运作管理分会、管理现代化研究会风险管理专业委员会等学术组织的理事等。

【内容简介】

Screening tasks that aim to identify a small subset of top alternatives from a large pool are common in business decision-making processes. These tasks often require substantial human effort to evaluate each alternative’s performance, making them time-consuming and costly. Motivated by recent advances in large language models (LLMs), particularly their ability to generate outputs that align well with human evaluations, we consider an LLM-as-human-evaluator approach for conducting screening virtually, thereby reducing the cost burden. To achieve scalability and cost-effectiveness in virtual screening, we identify that the stochastic nature of LLM outputs and their cost structure necessitate efficient budget allocation across all alternatives. To address this, we propose using a top-m greedy evaluation mechanism, a simple yet effective approach that keeps evaluating the current top-$m$ alternatives, and design the explore-first top-m greedy (EFG-m) algorithm. We prove that EFG-m is both sample-optimal and consistent in large-scale virtual screening. Surprisingly, we also uncover a bonus ranking effect, where the algorithm naturally induces an indifference-based ranking within the selected subset. To further enhance practicality, we design a suite of algorithm variants to improve screening performance and computational efficiency. Numerical experiments validate our results and demonstrate the effectiveness of our algorithms. Lastly, we conduct a case study on LLM-based virtual screening. The study shows that while LLMs alone may not provide meaningful screening and ranking results when directly queried, integrating them with our sample-optimal algorithms unlocks their potential for cost-effective, large-scale virtual screening.