Exploring the role of large language models in radiation emergency response
Creative Commons Attribution license..
In recent times, the field of artificial intelligence (AI) has been transformed by the introduction of large language models (LLMs). These models, popularized by OpenAI's GPT-3, have demonstrated the emergent capabilities of AI in comprehending and producing text resembling human language, which has helped them transform several industries. But its role has yet to be explored in the nuclear industry, specifically in managing radiation emergencies. The present work explores LLMs' contextual awareness, natural language interaction, and their capacity to comprehend diverse queries in a radiation emergency response setting. In this study we identify different user types and their specific LLM use-cases in radiation emergencies. Their possible interactions with ChatGPT, a popular LLM, has also been simulated and preliminary results are presented. Drawing on the insights gained from this exercise and to address concerns of reliability and misinformation, this study advocates for expert guided and domain-specific LLMs trained on radiation safety protocols and historical data. This study aims to guide radiation emergency management practitioners and decision-makers in effectively incorporating LLMs into their decision support framework.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2024 |
|---|---|
| Erschienen: |
2024 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:44 |
|---|---|
| Enthalten in: |
Journal of radiological protection : official journal of the Society for Radiological Protection - 44(2024), 1 vom: 15. Feb. |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Chandra, Anirudh [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
ChatGPT |
|---|
| Anmerkungen: |
Date Completed 16.02.2024 Date Revised 16.02.2024 published: Electronic Citation Status MEDLINE |
|---|
| doi: |
10.1088/1361-6498/ad270c |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM368141349 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM368141349 | ||
| 003 | DE-627 | ||
| 005 | 20240216232809.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 240208s2024 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1088/1361-6498/ad270c |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1296.xml |
| 035 | |a (DE-627)NLM368141349 | ||
| 035 | |a (NLM)38324900 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Chandra, Anirudh |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Exploring the role of large language models in radiation emergency response |
| 264 | 1 | |c 2024 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Completed 16.02.2024 | ||
| 500 | |a Date Revised 16.02.2024 | ||
| 500 | |a published: Electronic | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a Creative Commons Attribution license. | ||
| 520 | |a In recent times, the field of artificial intelligence (AI) has been transformed by the introduction of large language models (LLMs). These models, popularized by OpenAI's GPT-3, have demonstrated the emergent capabilities of AI in comprehending and producing text resembling human language, which has helped them transform several industries. But its role has yet to be explored in the nuclear industry, specifically in managing radiation emergencies. The present work explores LLMs' contextual awareness, natural language interaction, and their capacity to comprehend diverse queries in a radiation emergency response setting. In this study we identify different user types and their specific LLM use-cases in radiation emergencies. Their possible interactions with ChatGPT, a popular LLM, has also been simulated and preliminary results are presented. Drawing on the insights gained from this exercise and to address concerns of reliability and misinformation, this study advocates for expert guided and domain-specific LLMs trained on radiation safety protocols and historical data. This study aims to guide radiation emergency management practitioners and decision-makers in effectively incorporating LLMs into their decision support framework | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a ChatGPT | |
| 650 | 4 | |a disaster management | |
| 650 | 4 | |a emergency response | |
| 650 | 4 | |a large language models | |
| 650 | 4 | |a radiation emergency | |
| 700 | 1 | |a Chakraborty, Abinash |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Journal of radiological protection : official journal of the Society for Radiological Protection |d 1995 |g 44(2024), 1 vom: 15. Feb. |w (DE-627)NLM087787296 |x 1361-6498 |7 nnns |
| 773 | 1 | 8 | |g volume:44 |g year:2024 |g number:1 |g day:15 |g month:02 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1088/1361-6498/ad270c |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 44 |j 2024 |e 1 |b 15 |c 02 | ||