Evaluating Generative Ad Hoc Information Retrieval

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gienapp, Lukas, Scells, Harrisen, Deckers, Niklas, Bevendorff, Janek, Wang, Shuai, Kiesel, Johannes, Syed, Shahbaz, Fröbe, Maik, Zuccon, Guido, Stein, Benno, Hagen, Matthias, Potthast, Martin
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913358904557568
author Gienapp, Lukas
Scells, Harrisen
Deckers, Niklas
Bevendorff, Janek
Wang, Shuai
Kiesel, Johannes
Syed, Shahbaz
Fröbe, Maik
Zuccon, Guido
Stein, Benno
Hagen, Matthias
Potthast, Martin
author_facet Gienapp, Lukas
Scells, Harrisen
Deckers, Niklas
Bevendorff, Janek
Wang, Shuai
Kiesel, Johannes
Syed, Shahbaz
Fröbe, Maik
Zuccon, Guido
Stein, Benno
Hagen, Matthias
Potthast, Martin
contents Recent advances in large language models have enabled the development of viable generative retrieval systems. Instead of a traditional document ranking, generative retrieval systems often directly return a grounded generated text as a response to a query. Quantifying the utility of the textual responses is essential for appropriately evaluating such generative ad hoc retrieval. Yet, the established evaluation methodology for ranking-based ad hoc retrieval is not suited for the reliable and reproducible evaluation of generated responses. To lay a foundation for developing new evaluation methods for generative retrieval systems, we survey the relevant literature from the fields of information retrieval and natural language processing, identify search tasks and system architectures in generative retrieval, develop a new user model, and study its operationalization.
format Preprint
id arxiv_https___arxiv_org_abs_2311_04694
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Evaluating Generative Ad Hoc Information Retrieval
Gienapp, Lukas
Scells, Harrisen
Deckers, Niklas
Bevendorff, Janek
Wang, Shuai
Kiesel, Johannes
Syed, Shahbaz
Fröbe, Maik
Zuccon, Guido
Stein, Benno
Hagen, Matthias
Potthast, Martin
Information Retrieval
Computation and Language
Recent advances in large language models have enabled the development of viable generative retrieval systems. Instead of a traditional document ranking, generative retrieval systems often directly return a grounded generated text as a response to a query. Quantifying the utility of the textual responses is essential for appropriately evaluating such generative ad hoc retrieval. Yet, the established evaluation methodology for ranking-based ad hoc retrieval is not suited for the reliable and reproducible evaluation of generated responses. To lay a foundation for developing new evaluation methods for generative retrieval systems, we survey the relevant literature from the fields of information retrieval and natural language processing, identify search tasks and system architectures in generative retrieval, develop a new user model, and study its operationalization.
title Evaluating Generative Ad Hoc Information Retrieval
topic Information Retrieval
Computation and Language
url https://arxiv.org/abs/2311.04694