@inproceedings{jin-etal-2025-revisiting, title = "Revisiting 3{D} {LLM} Benchmarks: Are We Really Testing 3{D} Capabilities?", author = "Jin, Jiahe and He, Yanheng and Yang, Mingyan", editor = "Che, Wanxiang and Nabende, Joyce and Shutova, Ekaterina and Pilehvar, Mohammad Taher", booktitle = "Findings of the Association for Computational Linguistics: ACL 2025", month = jul, year = "2025", address = "Vienna, Austria", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/mtsummit-25-ingestion/2025.findings-acl.1222/", doi = "10.18653/v1/2025.findings-acl.1222", pages = "23858--23869", ISBN = "979-8-89176-256-5" }