A S.C.O.R.E. framework for evaluating open-ended responses from large language models in healthcare

Ting Fang Tan; Kabilan Elangovan; Jasmine Ong; Yuhe Ke; Aaron Lee; Nigam Shah; Joseph Sung; Tien Yin Wong; Lan Xue; Nan Liu; Haibo Wang; Chang Fu Kuo; Simon Chesterman; Zee Kin Yeong; Daniel S.W. Ting

doi:10.1016/j.xcrm.2026.102883

A S.C.O.R.E. framework for evaluating open-ended responses from large language models in healthcare

Ting Fang Tan
, Kabilan Elangovan
, Jasmine Ong
, Yuhe Ke
, Aaron Lee
, Nigam Shah
, Joseph Sung
, Tien Yin Wong
, Lan Xue
, Nan Liu
, Haibo Wang
, Chang Fu Kuo
, Simon Chesterman
, Zee Kin Yeong
, Daniel S.W. Ting

Research output: Contribution to journal › Article › peer-review

Abstract

Tan et al. proposed a S.C.O.R.E. framework to evaluate clinical responses from large language models (LLMs) in terms of Safety, Consensus & Context, Reproducibility, and Explainability. S.C.O.R.E. supports clinical LLM validation by providing structured, actionable insights to guide model optimization and refinement.

Original language	English
Article number	102883
Journal	Cell Reports Medicine
Volume	7
Issue number	7
DOIs	https://doi.org/10.1016/j.xcrm.2026.102883
State	Published - Jul 21 2026

Keywords

ChatGPT
Claude
DeepSeek
chatbots
evaluation
framework
healthcare
large language models
medicine

Access to Document

10.1016/j.xcrm.2026.102883

Cite this

@article{b017b951e909452e955d633e2e4f4470,

title = "A S.C.O.R.E. framework for evaluating open-ended responses from large language models in healthcare",

abstract = "Tan et al. proposed a S.C.O.R.E. framework to evaluate clinical responses from large language models (LLMs) in terms of Safety, Consensus \& Context, Reproducibility, and Explainability. S.C.O.R.E. supports clinical LLM validation by providing structured, actionable insights to guide model optimization and refinement.",

keywords = "ChatGPT, Claude, DeepSeek, chatbots, evaluation, framework, healthcare, large language models, medicine",

author = "Tan, \{Ting Fang\} and Kabilan Elangovan and Jasmine Ong and Yuhe Ke and Aaron Lee and Nigam Shah and Joseph Sung and Wong, \{Tien Yin\} and Lan Xue and Nan Liu and Haibo Wang and Kuo, \{Chang Fu\} and Simon Chesterman and Yeong, \{Zee Kin\} and Ting, \{Daniel S.W.\}",

note = "Publisher Copyright: {\textcopyright} 2026 The Authors. Published by Elsevier Inc. This is an open access article under the CC BY-NC-ND license. http://creativecommons.org/licenses/by-nc-nd/4.0/",

year = "2026",

month = jul,

day = "21",

doi = "10.1016/j.xcrm.2026.102883",

language = "English",

volume = "7",

journal = "Cell Reports Medicine",

issn = "2666-3791",

number = "7",

}

TY - JOUR

T1 - A S.C.O.R.E. framework for evaluating open-ended responses from large language models in healthcare

AU - Tan, Ting Fang

AU - Elangovan, Kabilan

AU - Ong, Jasmine

AU - Ke, Yuhe

AU - Lee, Aaron

AU - Shah, Nigam

AU - Sung, Joseph

AU - Wong, Tien Yin

AU - Xue, Lan

AU - Liu, Nan

AU - Wang, Haibo

AU - Kuo, Chang Fu

AU - Chesterman, Simon

AU - Yeong, Zee Kin

AU - Ting, Daniel S.W.

PY - 2026/7/21

Y1 - 2026/7/21

N2 - Tan et al. proposed a S.C.O.R.E. framework to evaluate clinical responses from large language models (LLMs) in terms of Safety, Consensus & Context, Reproducibility, and Explainability. S.C.O.R.E. supports clinical LLM validation by providing structured, actionable insights to guide model optimization and refinement.

AB - Tan et al. proposed a S.C.O.R.E. framework to evaluate clinical responses from large language models (LLMs) in terms of Safety, Consensus & Context, Reproducibility, and Explainability. S.C.O.R.E. supports clinical LLM validation by providing structured, actionable insights to guide model optimization and refinement.

KW - ChatGPT

KW - Claude

KW - DeepSeek

KW - chatbots

KW - evaluation

KW - framework

KW - healthcare

KW - large language models

KW - medicine

UR - https://www.scopus.com/pages/publications/105044241802

U2 - 10.1016/j.xcrm.2026.102883

DO - 10.1016/j.xcrm.2026.102883

M3 - Article

C2 - 42349414

AN - SCOPUS:105044241802

SN - 2666-3791

VL - 7

JO - Cell Reports Medicine

JF - Cell Reports Medicine

IS - 7

M1 - 102883

ER -

A S.C.O.R.E. framework for evaluating open-ended responses from large language models in healthcare

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this