Back
Generative Large Language Models have emerged as useful tools, reshaping professional workflows. However, their efficacy in inherently complex and human-centric tasks such as leadership and strategic planning remains under-explored. In this interdisciplinary study, we present a novel dataset and compare LLMs and human leaders in the context of work-place action planning, specifically focusing on translating the abstract idea of inclusion into actionable SMART goals. We developed the Leader Success Bot, a script-based chat-bot co-designed with domain experts, to guide more than 250 real-life leaders in generating inclusive workplace action plans. We systematically prompted seven state-of-the-art chat-based LLMs to perform the same task using the socio-demographic data of real-life leaders and instructions co-developed with domain experts. Our publicly released dataset enables direct comparison between human and LLM-generated workplace action plans, offering in-sights into their respective strengths, biases, and limitations. Our findings highlight critical gaps and opportunities for LLMs in leadership applications, fostering interdisciplinary collaboration and NLP applications.
@conference{InclusiveLeadershipintheAgeofAISingh2025, title = {Inclusive Leadership in the Age of AI: A Dataset and Comparative Study of LLMs vs. Real-Life Leaders in Workplace Action Planning}, booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2025}, abstract = {Generative Large Language Models have emerged as useful tools, reshaping professional workflows. However, their efficacy in inherently complex and human-centric tasks such as leadership and strategic planning remains under-explored. In this interdisciplinary study, we present a novel dataset and compare LLMs and human leaders in the context of work-place action planning, specifically focusing on translating the abstract idea of inclusion into actionable SMART goals. We developed the Leader Success Bot, a script-based chat-bot co-designed with domain experts, to guide more than 250 real-life leaders in generating inclusive workplace action plans. We systematically prompted seven state-of-the-art chat-based LLMs to perform the same task using the socio-demographic data of real-life leaders and instructions co-developed with domain experts. Our publicly released dataset enables direct comparison between human and LLM-generated workplace action plans, offering in-sights into their respective strengths, biases, and limitations. Our findings highlight critical gaps and opportunities for LLMs in leadership applications, fostering interdisciplinary collaboration and NLP applications.}, pages = {19732-19753}, publisher = {Association for Computational Linguistics}, organization = {Association for Computational Linguistics}, address = {Suzhou, China}, month = nov, year = {2025}, author = {Singh, Vindhya and Schulte im Walde, Sabine and Keplinger, Ksenia}, doi = {10.18653/v1/2025.findings-emnlp.1075}, url = {https://aclanthology.org/anthology-files/anthology-files/pdf/findings/2025.findings-emnlp.1075.pdf}, month_numeric = {11} }
More information