BIRCO: A Benchmark of Information Retrieval Tasks with Complex Objectives

We present the Benchmark of Information Retrieval (IR) tasks with Complex Objectives (BIRCO). BIRCO evaluates the ability of IR systems to retrieve documents given multi-faceted user objectives. The benchmark's complexity and compact size make it suitable for evaluating large language model (LL...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-04
Hauptverfasser:	Wang, Xiaoyue, Wang, Jianyou, Cao, Weili, Wang, Kaicheng, Paturi, Ramamohan, Bergen, Leon
Format:	Artikel
Sprache:	eng
Schlagworte:	Benchmarks Information retrieval Large language models Modular systems Task complexity
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!