Limitations of Automatic Relevance Assessments with Large Language Models for Fair and Reliable Retrieval Evaluation.

@inproceedings{otero-2025-limitations, author = {David Otero and Javier Parapar and \'{A}lvaro Barreiro}, editor = {Nicola Ferro and Maria Maistro and Gabriella Pasi and Omar Alonso and Andrew Trotman and Suzan Verberne}, title = {{Limitations of Automatic Relevance Assessments with Large Language Models for Fair and Reliable Retrieval Evaluation}}, 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 = {2545--2549}, publisher = {ACM}, year = {2025}, url = {https://doi.org/10.1145/3726302.3730221}, doi = {https://doi.org/10.1145/3726302.3730221} }