Multi-stage Large Language Model Pipelines Can Outperform GPT-4o in Relevance Assessment.

@inproceedings{schnabel-2025-multistage, author = {Julian A. Schnabel and Johanne R. Trippas and Falk Scholer and Danula Hettiachchi}, editor = {Guodong Long and Michale Blumestein and Yi Chang and Liane Lewin-Eytan and Zi Huang and Elad Yom-Tov}, title = {{Multi-stage Large Language Model Pipelines Can Outperform GPT-4o in Relevance Assessment}}, booktitle = {{Companion Proceedings of the ACM on Web Conference 2025, WWW 2025, Sydney, NSW, Australia, 28 April 2025 - 2 May 2025}}, pages = {1288--1292}, publisher = {ACM}, year = {2025}, url = {https://doi.org/10.1145/3701716.3715488}, doi = {https://doi.org/10.1145/3701716.3715488} }