Murugadoss et al. "Evaluating the Evaluator: Measuring LLMs' Adherence to Task Evaluation Instructions." AAAI Conference on Artificial Intelligence, 2025. doi:10.1609/AAAI.V39I18.34157
Markdown
[Murugadoss et al. "Evaluating the Evaluator: Measuring LLMs' Adherence to Task Evaluation Instructions." AAAI Conference on Artificial Intelligence, 2025.](https://mlanthology.org/aaai/2025/murugadoss2025aaai-evaluating/) doi:10.1609/AAAI.V39I18.34157
BibTeX
@inproceedings{murugadoss2025aaai-evaluating,
title = {{Evaluating the Evaluator: Measuring LLMs' Adherence to Task Evaluation Instructions}},
author = {Murugadoss, Bhuvanashree and Pölitz, Christian and Drosos, Ian and Le, Vu and McKenna, Nick and Negreanu, Carina Suzana and Parnin, Chris and Sarkar, Advait},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2025},
pages = {19589-19597},
doi = {10.1609/AAAI.V39I18.34157},
url = {https://mlanthology.org/aaai/2025/murugadoss2025aaai-evaluating/}
}