Mayfield, J.
, Yang, E.
, Lawrie, D.
, MacAvaney, S.
, McNamee, P.
, Oard, D.
, Soldaini, L.
, Soboroff, I.
, Weller, O.
, Kayi, E.
, Sanders, K.
, Mason, M.
and Hibbler, N.
(2024),
On the Evaluation of Machine-Generated Reports, Proceedings of ACM SIGIR 2024, Washington, DC, US, [online], https://doi.org/10.1145/3626772.3657846, https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=957812
(Accessed December 21, 2024)
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
Secure .gov websites use HTTPS
A lock (
) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.
On the Evaluation of Machine-Generated Reports
Published
Author(s)
James Mayfield, Eugene Yang, Dawn Lawrie, Sean MacAvaney, Paul McNamee, Douglas Oard, Luca Soldaini, , Orion Weller, Efsun Kayi, Kate Sanders, Marc Mason, Noah Hibbler
Abstract
Large Language Models (LLMs) have enabled new ways to satisfy information needs. Although great strides have been made in applying them to settings like document ranking and short-form text generation, they still struggle to compose complete, accurate, and verifiable long-form reports. Reports with these qualities are necessary to satisfy the complex, nuanced, or multi-faceted information needs of users. In this perspective paper, we draw together opinions from industry and academia, and from a variety of related research areas, to present our vision for automatic report generation, and— critically—a flexible framework by which such reports can be evaluated. In contrast with other summarization tasks, automatic report generation starts with a detailed description of an information need, stating the necessary background, requirements, and scope of the report. Further, the generated reports should be complete, accurate, and verifiable. These qualities, which are desirable—if not required— in many analytic report-writing settings, require rethinking how to build and evaluate systems that exhibit these qualities. To foster new efforts in building these systems, we present an evaluation framework that draws on ideas found in various evaluations. To test completeness and accuracy, the framework uses nuggets of information, expressed as questions and answers, that need to be part of any high-quality generated report. Additionally, evaluation of citations that map claims made in the report to their source documents ensures verifiability.Proceedings Title
Proceedings of ACM SIGIR 2024
Conference Dates
July 15-19, 2024
Conference Location
Washington, DC, US
Conference Title
ACM SIGIR 2024
Pub Type
Conferences
Download Paper
Keywords
generative AI, AI evaluation
Citation
Issues
If you have any questions about this publication or are having problems accessing it, please contact reflib@nist.gov.
Created July 14, 2024, Updated October 1, 2024