Language conveys cultural identity even when not intentionally disclosed. This study examines cultural signals in task-oriented dialogue using English negotiations from the KODIS dataset. We focus our analysis on participants from four countries: the US, UK, Mexico, and South Korea. Interacting anonymously under identical conditions, we evaluated whether a speaker’s country could be inferred from dialogue by zero-shot LLMs and embedding-based classifiers. Results show that while objective negotiation outcomes remained similar across groups, subjective perceptions varied significantly. Embedding-based models reliably identified country of origin, whereas zero-shot LLM performance dropped under distribution shift. These findings suggest that cultural identity-related signals are embedded in language and may be relevant for analyzing negotiation dialogue.

Social determinants of health (SDOH) documented in the electronic health record through unstructured text are increasingly being studied to understand how SDOH impacts patient health outcomes. In this work, we utilize the Social History Annotation Corpus (SHAC), a multi-institutional corpus of de-identified social history sections annotated for SDOH, including substance use, employment, and living status information. We explore the automatic extraction of SDOH information with SHAC in both standoff and inline annotation formats using GPT-4 in a one-shot prompting setting. We compare GPT-4 extraction performance with a high-performing supervised approach and perform thorough error analyses. Our prompt-based GPT-4 method achieved an overall 0.652 F1 on the SHAC test set, similar to the 7th best-performing system among all teams in the n2c2 challenge with SHAC.