Large Language Model Relevance Assessors Agree With One Another More Than With Human Assessors.

@inproceedings{an-2025-large, author = {Guoyuan An and Maik Fr\"{o}be and Andrew Parry and Wei Guo and Ferdinand Schlatt and Yong Liu and Guoyuan An and Maik Fr\"{o}be and Sean MacAvaney and Xiao-Ming Wu and Andrew Parry and Wei Guo and Benno Stein and Ferdinand Schlatt and Yong Liu and Martin Potthast and Sean MacAvaney and Xiao-Ming Wu and Matthias Hagen}, editor = {Nicola Ferro and Maria Maistro and Gabriella Pasi and Omar Alonso and Andrew Trotman and Suzan Verberne}, title = {{Large Language Model Relevance Assessors Agree With One Another More Than With Human Assessors}}, booktitle = {{Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2025, Padua, Italy, July 13-18, 2025}}, pages = {2858--2863}, publisher = {ACM}, year = {2025}, url = {https://doi.org/10.1145/3726302.3730218}, doi = {https://doi.org/10.1145/3726302.3730218} }