Can I read BIRCO: A Benchmark of Information Retrieval Tasks with Complex Objectives on EtoBox?

BIRCO: A Benchmark of Information Retrieval Tasks with Complex Objectives by Wang, Xiaoyue; Wang, Jianyou; Cao, Weili; Wang, Kaicheng; Paturi, Ramamohan; Bergen, Leon is a scholarly article available to read on EtoBox.

What is BIRCO: A Benchmark of Information Retrieval Tasks with Complex Objectives about?

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 (LLM)-based information retrieval systems. We present a modular framework for investigating factors that may influence LLM performance on retrieval tasks, and identify a simple baseline model which matches or outperforms existing approaches and more complex alternatives. No approach achieves satisfactory performance on all benchmark tasks, suggesting that stronger models and new retrieval protocols are necessary to address complex user needs.

Author

Wang, Xiaoyue; Wang, Jianyou; Cao, Weili; Wang, Kaicheng; Paturi, Ramamohan; Bergen, Leon

Published

2024

Language

EN