The Challenges of Evaluating LLM Applications: An Analysis of Automated, Human, and LLM-Based Approaches.

@inproceedings{abeysinghe-2024-challenges, author = {Bhashithe Abeysinghe and Ruhan Circi}, editor = {Clemencia Siro and Mohammad Aliannejadi and Hossein A. Rahmani and Nick Craswell and Charles L. A. Clarke and Guglielmo Faggioli and Bhaskar Mitra and Paul Thomas and Emine Yilmaz}, title = {{The Challenges of Evaluating LLM Applications: An Analysis of Automated, Human, and LLM-Based Approaches}}, booktitle = {{Proceedings of The First Workshop on Large Language Models for Evaluation in Information Retrieval (LLM4Eval 2024) co-located with 10th International Conference on Online Publishing (SIGIR 2024), Washington D.C., USA, July 18, 2024}}, series = {CEUR Workshop Proceedings}, volume = {3752}, pages = {4--18}, publisher = {CEUR-WS.org}, year = {2024}, url = {https://ceur-ws.org/Vol-3752/paper1.pdf} }