EUVIMEDEUVIMED entdecken
Crossref

Predicting Workers’ Compensation Dispute Outcomes with Large Language Models

Vajira A. Manathunga, Duyen Hai Doan

Variance · 23.01.2026 · 19

DOI: 10.66573/001c.154307 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Variance, online erschienen am 23.01.2026. Verfasst von Vajira A. Manathunga und 1 weiteren Autor:innen. Die Arbeit nennt 53 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Workers’ compensation insurance is one of the oldest social insurance programs in the United States, predating both Social Security and unemployment insurance. When disputes arise between employees and employers over benefit entitlements, most states require resolution through administrative boards. In this study, we evaluate whether large language models (LLMs) can predict the outcomes of workers’ compensation cases more accurately than traditional, domain-specific natural language processing (NLP) techniques under the zero-shot learning paradigm. We compare performance under two input scenarios: using only the initial “Issues” filed and using the full “Findings of Fact” narrative of each case, and we measure predictive accuracy against actual board decisions. Our results show that, with access to a sufficiently large context window, LLMs match or surpass the performance of specialized NLP pipelines despite having no task-specific training on workers’ compensation data. This finding underscores the practical utility of LLMs in case outcomes for the plaintiff, the employer, actuaries, and the insurance carrier.

Zitieren

APA

Manathunga, V. A., & Doan, D. H. (2026). Predicting Workers’ Compensation Dispute Outcomes with Large Language Models. Variance, 19. https://doi.org/10.66573/001c.154307

Vancouver

Manathunga VA, Doan DH. Predicting Workers’ Compensation Dispute Outcomes with Large Language Models. Variance. 2026;19. doi:10.66573/001c.154307

BibTeX
@article{Manathunga2026,
  author = {Manathunga, Vajira A. and Doan, Duyen Hai},
  title = {Predicting Workers’ Compensation Dispute Outcomes with Large Language Models},
  journal = {Variance},
  year = {2026},
  volume = {19},
  doi = {10.66573/001c.154307}
}
Kostenlos starten →