Auto-ARGUE: LLM-Based Report Generation Evaluation.

@inproceedings{walden-2026-autoargue, author = {William Gantt Walden and Ying Du and Bryan Li and Yanen Li and Marc Mason and Nobuyuki Shimizu and Bo-June Paul Hsu and Gabrielle K. Liu and William Gantt Walden and Ying Du and Orion Weller and Tomek Strzalkowski and ChengXiang Zhai and Yu Hou and Laura Dietz and Ting Liu and Dawn J. Lawrie and Shenzheng Zhang and James Mayfield and Kuansan Wang and John M. Conroy and Xinyang Zhang and Neil P. Molino and Hannah Recknor and Bryan Li and Yanen Li and Bo-June Paul Hsu and Gabrielle K. Liu and ChengXiang Zhai and Yu Hou and Dawn J. Lawrie and Shenzheng Zhang and James Mayfield and Kuansan Wang and Eugene Yang}, editor = {Hannah Bast and Alistair Moffat and Falk Scholer and Marc Najork and Min Zhang and Hannah Bast and Marc Najork and Min Zhang}, title = {{Auto-ARGUE: LLM-Based Report Generation Evaluation}}, booktitle = {{Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2026, MelbourneVICAustralia, July 20-24, 2026}}, pages = {5235--5239}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3805712.3808384}, doi = {https://doi.org/10.1145/3805712.3808384} }