Plans for Evaluating Structured Generative Search Summaries
Information Retrieval
2026-05-27 v1 Artificial Intelligence
Abstract
We propose a framework for evaluating structured generative search summaries that are placed atop organic web search results. A structured summary, generated by a large language model, typically consists of an overview, several sections with section titles, and a list of source documents that are cited within the summary. We then describe our plans for implementing and evaluating the framework.
Cite
@article{arxiv.2605.26400,
title = {Plans for Evaluating Structured Generative Search Summaries},
author = {Tetsuya Sakai and Jina Lee and Hanpei Fang and Young-In Song},
journal= {arXiv preprint arXiv:2605.26400},
year = {2026}
}
Comments
8 pages (including 2 pages for references)