paper-with-me

Papers

Submodular Evaluation Subset Selection in Automatic Prompt Optimization

2026-01-07 · Jinming Nian, Zhiyuan Peng, Hongwei Shang, Dae Hoon Park, Yi Fang arxiv

Automatic prompt optimization reduces manual prompt engineering, but relies on task performance measured on a small, often randomly sampled evaluation subset as its main source of feedback signal. Despite this, how to select that evaluation subset is usually treated as an implementation detail. We study evaluation subset selection for prompt optimization from a principled perspective and propose SESS, a submodular evaluation subset selection method. We frame selection as maximizing an objective set function and show that, under mild conditions, it is monotone and submodular, enabling greedy selection with theoretical guarantees. Across GSM8K, MATH, and GPQA-Diamond, submodularly selected evaluation subsets can yield better optimized prompts than random or heuristic baselines.

📄 PDF Abstract BibTeX arXiv:2601.03493

Code (0)

등록된 구현이 없습니다.

Tasks

Prompt Engineering

Similar Papers 제목 키워드 기반

Sub-SA: Strengthen In-context Learning via Submodular Selective Annotation

2024-07-08 · Jian Qian, Miao Sun, Sifan Zhou, Ziyu Zhao 외

In-context learning (ICL) leverages in-context examples as prompts for the predictions of Large Language Models (LLMs). These prompts play a crucial role in achieving strong performance. However, the selection of suitabl…

DiversityIn-Context Learning

Select Smarter, Not More: Prompt-Aware Evaluation Scheduling with Submodular Guarantees

2026-04-13 · Xiaoyu Ma, Yiwen Li, Haoyue Liu, Zhichao Wang 외 arxiv

Automatic prompt optimization (APO) hinges on the quality of its evaluation signal, yet scoring every prompt candidate on the full training set is prohibitively expensive. Existing methods either fix a single evaluation …

Causal meets Submodular: Subset Selection with Directed Information

2016-12-01 · NeurIPS 2016 12 · Yuxun Zhou, Costas J. Spanos

We study causal subset selection with Directed Information as the measure of prediction causality. Two typical tasks, causal sensor placement and covariate selection, are correspondingly formulated into cardinality const…

Multinoulli Extension: A Lossless Continuous Relaxation for Partition-Constrained Subset Selection

2026-03-23 · Qixin Zhang, Wei Huang, Yan Sun, Yao Shu 외 arxiv

Identifying the most representative subset for a close-to-submodular objective while satisfying the predefined partition constraint is a fundamental task with numerous applications in machine learning. However, the exist…

Maximizing Submodular Functions for Recommendation in the Presence of Biases

2023-05-03 · Anay Mehrotra, Nisheeth K. Vishnoi

Subset selection tasks, arise in recommendation systems and search engines and ask to select a subset of items that maximize the value for the user. The values of subsets often display diminishing returns, and hence, sub…

FairnessRecommendation Systems