EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

How good are large language models at product risk assessment?

Zachary A Collier, Richard J Gruss, Alan S Abrahams

Risk Analysis · 2025-04 · 45 (4) · 766-789

DOI: 10.1111/risa.14351 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Risk Analysis, online erschienen am 08.06.2024. Verfasst von Zachary A Collier und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Management, Radford University, Radford, Virginia, USA. Hauptthemen laut MEDLINE: Artificial Intelligence, Consumer Product Safety. Die Arbeit wurde bisher 27-mal zitiert (Crossref) und nennt 77 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Product safety professionals must assess the risks to consumers associated with the foreseeable uses and misuses of products. In this study, we investigate the utility of generative artificial intelligence (AI), specifically large language models (LLMs) such as ChatGPT, across a number of tasks involved in the product risk assessment process. For a set of six consumer products, prompts were developed related to failure mode identification, the construction and population of a failure mode and effects analysis (FMEA) table, risk mitigation identification, and guidance to product designers, users, and regulators. These prompts were input into ChatGPT and the outputs were recorded. A survey was administered to product safety professionals to ascertain the quality of the outputs. We found that ChatGPT generally performed better at divergent thinking tasks such as brainstorming potential failure modes and risk mitigations. However, there were errors and inconsistencies in some of the results, and the guidance provided was perceived as overly generic, occasionally outlandish, and not reflective of the depth of knowledge held by a subject matter expert. When tested against a sample of other LLMs, similar patterns in strengths and weaknesses were demonstrated. Despite these challenges, a role for LLMs may still exist in product risk assessment to assist in ideation, while experts may shift their focus to critical review of AI‐generated content.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligenceConsumer Product SafetyRisk AssessmentHumansLarge Language Models

Stichwörter der Autor:innen

FMEAGenerative AIProduct safety

Autor:innen und Institutionen

  • Department of Management, Radford University, Radford, Virginia, USA.
  • Department of Business Information Technology, Virginia Tech, Blacksburg, Virginia, USA.

Zitieren

APA

Collier, Z. A., Gruss, R. J., & Abrahams, A. S. (2025). How good are large language models at product risk assessment?. Risk Analysis, 45(4), 766-789. https://doi.org/10.1111/risa.14351

Vancouver

Collier ZA, Gruss RJ, Abrahams AS. How good are large language models at product risk assessment?. Risk Analysis. 2025;45(4):766-789. doi:10.1111/risa.14351

BibTeX
@article{Collier2025,
  author = {Collier, Zachary A and Gruss, Richard J and Abrahams, Alan S},
  title = {How good are large language models at product risk assessment?},
  journal = {Risk Analysis},
  year = {2025},
  volume = {45},
  number = {4},
  pages = {766--789},
  doi = {10.1111/risa.14351}
}
Kostenlos starten →