EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Infusing behavior science into large language models for activity coaching

Narayan Hegde iD, Madhurima Vardhan, Deepak Nathani, Emily Rosenzweig, Cathy Speed, Alan Karthikesalingam, Martin Seneviratne

PLOS Digital Health · 02.04.2024 · 3 (4) · e0000431

DOI: 10.1371/journal.pdig.0000431 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Digital Health, online erschienen am 02.04.2024. Verfasst von Narayan Hegde und 6 weiteren Autor:innen. Beteiligte Einrichtung: Google Research, Bangalore, India. Die Arbeit wurde bisher 36-mal zitiert (Crossref) und nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Large language models (LLMs) have shown promise for task-oriented dialogue across a range of domains. The use of LLMs in health and fitness coaching is under-explored. Behavior science frameworks such as COM-B, which conceptualizes behavior change in terms of capability (C), Opportunity (O) and Motivation (M), can be used to architect coaching interventions in a way that promotes sustained change. Here we aim to incorporate behavior science principles into an LLM using two knowledge infusion techniques: coach message priming (where exemplar coach responses are provided as context to the LLM), and dialogue re-ranking (where the COM-B category of the LLM output is matched to the inferred user need). Simulated conversations were conducted between the primed or unprimed LLM and a member of the research team, and then evaluated by 8 human raters. Ratings for the primed conversations were significantly higher in terms of empathy and actionability. The same raters also compared a single response generated by the unprimed, primed and re-ranked models, finding a significant uplift in actionability and empathy from the re-ranking technique. This is a proof of concept of how behavior science frameworks can be infused into automated conversational agents for a more principled coaching experience.

Autor:innen und Institutionen

  • Google Research, Bangalore, India.
  • Verily Life Sciences, San Francisco, United States of America.
  • Google Health, London, United Kingdom.

ORCID-Profile: Narayan Hegde

Zitieren

APA

Hegde, N., Vardhan, M., Nathani, D., Rosenzweig, E., Speed, C., Karthikesalingam, A., & Seneviratne, M. (2024). Infusing behavior science into large language models for activity coaching. PLOS Digital Health, 3(4), e0000431. https://doi.org/10.1371/journal.pdig.0000431

Vancouver

Hegde N, Vardhan M, Nathani D, Rosenzweig E, Speed C, Karthikesalingam A, et al. Infusing behavior science into large language models for activity coaching. PLOS Digital Health. 2024;3(4):e0000431. doi:10.1371/journal.pdig.0000431

BibTeX
@article{Hegde2024,
  author = {Hegde, Narayan and Vardhan, Madhurima and Nathani, Deepak and Rosenzweig, Emily and Speed, Cathy and Karthikesalingam, Alan and Seneviratne, Martin},
  title = {Infusing behavior science into large language models for activity coaching},
  journal = {PLOS Digital Health},
  year = {2024},
  volume = {3},
  number = {4},
  pages = {e0000431},
  doi = {10.1371/journal.pdig.0000431}
}
Kostenlos starten →