Living Map of Generative LLM-Based Tools for Health and Social Care Applications

Ian Shemilt; Gareth J. Hollands; Claire Louise Khouja; Gary Austin Raine; James Thomas

Living Map of Generative LLM-Based Tools for Health and Social Care Applications

Ian Shemilt, Gareth J. Hollands, Claire Louise Khouja, Gary Austin Raine, James Thomas

Centre for Reviews and Dissemination

Research output: Other contribution

Abstract

This living map of research contains bibliographic records of studies about generative large language model- (LLM-) based tools for health and social care applications.

We identify studies using a semi-automated continual evidence surveillance workflow featuring automated searches of a large open access knowledge graph dataset -- containing records of 250 million research articles from across science -- using OpenAlex tools in EPPI Reviewer. See 'About this Map' (.docx) for further details.

The main reason this map focuses on studies of generative LLM-based tools - and does not contain studies of other kinds of (non-generative) artificial intelligence (AI) or machine learning tools - is that the possibility of generative LLM-based tools producing reliable, or accurate, responses is dependent on unique features of their design that the other kinds of tools do not share.

Original language	English
Type	Map of evidence
Media of output	Online
Publisher	EPPI Centre, UCL Social Research Institute, UCL Institute of Education, University College London
Number of pages	1
Place of Publication	London
Publication status	Published - 2 Sept 2024

Keywords

LLMs
Large Language Model
ChatGPT
Claude

Access to Document

https://eppi.ioe.ac.uk/cms/Default.aspx?tabid=3938Licence: CC BY-NC

Cite this

@misc{f8d95bfb8fb24c8e9325dd8cdf5cd965,

title = "Living Map of Generative LLM-Based Tools for Health and Social Care Applications",

abstract = "This living map of research contains bibliographic records of studies about generative large language model- (LLM-) based tools for health and social care applications.We identify studies using a semi-automated continual evidence surveillance workflow featuring automated searches of a large open access knowledge graph dataset -- containing records of 250 million research articles from across science -- using OpenAlex tools in EPPI Reviewer. See 'About this Map' (.docx) for further details. The main reason this map focuses on studies of generative LLM-based tools - and does not contain studies of other kinds of (non-generative) artificial intelligence (AI) or machine learning tools - is that the possibility of generative LLM-based tools producing reliable, or accurate, responses is dependent on unique features of their design that the other kinds of tools do not share. ",

keywords = "LLMs, Large Language Model, ChatGPT, Claude",

author = "Ian Shemilt and Hollands, {Gareth J.} and Khouja, {Claire Louise} and Raine, {Gary Austin} and James Thomas",

year = "2024",

month = sep,

day = "2",

language = "English",

publisher = "EPPI Centre, UCL Social Research Institute, UCL Institute of Education, University College London",

type = "Other",

}

TY - GEN

T1 - Living Map of Generative LLM-Based Tools for Health and Social Care Applications

AU - Shemilt, Ian

AU - Hollands, Gareth J.

AU - Khouja, Claire Louise

AU - Raine, Gary Austin

AU - Thomas, James

PY - 2024/9/2

Y1 - 2024/9/2

N2 - This living map of research contains bibliographic records of studies about generative large language model- (LLM-) based tools for health and social care applications.We identify studies using a semi-automated continual evidence surveillance workflow featuring automated searches of a large open access knowledge graph dataset -- containing records of 250 million research articles from across science -- using OpenAlex tools in EPPI Reviewer. See 'About this Map' (.docx) for further details. The main reason this map focuses on studies of generative LLM-based tools - and does not contain studies of other kinds of (non-generative) artificial intelligence (AI) or machine learning tools - is that the possibility of generative LLM-based tools producing reliable, or accurate, responses is dependent on unique features of their design that the other kinds of tools do not share.

AB - This living map of research contains bibliographic records of studies about generative large language model- (LLM-) based tools for health and social care applications.We identify studies using a semi-automated continual evidence surveillance workflow featuring automated searches of a large open access knowledge graph dataset -- containing records of 250 million research articles from across science -- using OpenAlex tools in EPPI Reviewer. See 'About this Map' (.docx) for further details. The main reason this map focuses on studies of generative LLM-based tools - and does not contain studies of other kinds of (non-generative) artificial intelligence (AI) or machine learning tools - is that the possibility of generative LLM-based tools producing reliable, or accurate, responses is dependent on unique features of their design that the other kinds of tools do not share.

KW - LLMs

KW - Large Language Model

KW - ChatGPT

KW - Claude

M3 - Other contribution

PB - EPPI Centre, UCL Social Research Institute, UCL Institute of Education, University College London

CY - London

ER -