Open-World Evaluation for Retrieving Diverse Perspectives
Published in 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics, 2025
This paper introduces a new evaluation framework for retrieving diverse perspectives in open-world question answering settings. We present BERDS (Benchmarking Evaluation for Retrieving Diverse Sources), which addresses the challenge of evaluating retrieval systems when the space of valid perspectives is not pre-defined.
Website | Paper |
Recommended citation: Hung-Ting Chen, Eunsol Choi. (2025). "Open-World Evaluation for Retrieving Diverse Perspectives." 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics.
Download Paper