TY - GEN
T1 - Beyond Human Labels
T2 - 30th Conference on Empirical Methods in Natural Language Processing, EMNLP 2025
AU - Ling, Zijian
AU - Zhang, Han
AU - Cui, Jiahao
AU - Wu, Zhequn
AU - Sun, Xu
AU - Li, Guohao
AU - He, Xiangjian
N1 - Publisher Copyright:
© 2025 Association for Computational Linguistics.
PY - 2025
Y1 - 2025
N2 - Efficient resume parsing is critical for global hiring, yet the absence of dedicated benchmarks for evaluating large language models (LLMs) on multilingual, structure-rich resumes hinders progress. To address this, we introduce ResumeBench, the first privacy-compliant benchmark comprising 2,500 synthetic resumes spanning 50 templates, 30 career fields, and 5 languages. These resumes are generated through a human-in-the-loop pipeline that prioritizes realism, diversity, and privacy compliance, which are validated against real-world resumes. This paper evaluates 24 state-of-the-art LLMs on ResumeBench, revealing substantial variations in handling resume complexities. Specifically, top-performing models like GPT-4o exhibit challenges in cross-lingual structural alignment while smaller models show inconsistent scaling effects. Code-specialized LLMs underperform relative to generalists, while JSON outputs enhance schema compliance but fail to address semantic ambiguities. Our findings underscore the necessity for domain-specific optimization and hybrid training strategies to enhance structural and contextual reasoning in LLMs.
AB - Efficient resume parsing is critical for global hiring, yet the absence of dedicated benchmarks for evaluating large language models (LLMs) on multilingual, structure-rich resumes hinders progress. To address this, we introduce ResumeBench, the first privacy-compliant benchmark comprising 2,500 synthetic resumes spanning 50 templates, 30 career fields, and 5 languages. These resumes are generated through a human-in-the-loop pipeline that prioritizes realism, diversity, and privacy compliance, which are validated against real-world resumes. This paper evaluates 24 state-of-the-art LLMs on ResumeBench, revealing substantial variations in handling resume complexities. Specifically, top-performing models like GPT-4o exhibit challenges in cross-lingual structural alignment while smaller models show inconsistent scaling effects. Code-specialized LLMs underperform relative to generalists, while JSON outputs enhance schema compliance but fail to address semantic ambiguities. Our findings underscore the necessity for domain-specific optimization and hybrid training strategies to enhance structural and contextual reasoning in LLMs.
UR - https://www.scopus.com/pages/publications/105040269275
U2 - 10.18653/v1/2025.emnlp-main.1626
DO - 10.18653/v1/2025.emnlp-main.1626
M3 - Conference contribution
AN - SCOPUS:105040269275
T3 - EMNLP 2025 - 2025 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference
SP - 31919
EP - 31945
BT - EMNLP 2025 - 2025 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference
A2 - Christodoulopoulos, Christos
A2 - Chakraborty, Tanmoy
A2 - Rose, Carolyn
A2 - Peng, Violet
PB - Association for Computational Linguistics (ACL)
Y2 - 4 November 2025 through 9 November 2025
ER -