Luning Sun

Luning Sun

Auto-generated profile, based on publicly available information

Luning Sun

The Psychometrics Centre, University of Cambridge, Cambridge, UK

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 August 2023 in Research Square
Verified
Preprint
Open access
PDF file
GSGregory Serapio-García
Gregory Serapio-García
MSMustafa Safdari
Mustafa Safdari
CCClément Crepy
Clément Crepy
LSLuning Sun
Luning Sun
SFStephen Fitz
Stephen Fitz
MMMaja Mataric
Maja Mataric
The advent of large language models (LLMs) has revolutionized natural language processing, enabling the generation of coherent and contextually relevant text. As LLMs increasingly power conversational agents, the synthetic personality embedded in these models, by virtue of training on large amounts of human data, is becoming increasingly important. Since personality is a key factor determining the effectiveness of communication, we present a comprehensive method for administering and validating personality tests on widely-used LLMs, as well as for shaping personality in the generated text of such LLMs. Applying this method, we found: 1) personality measurements in the outputs of some LLMs under specific prompting configurations are reliable and valid; 2) evidence of reliability and validity of synthetic LLM personality is stronger for larger and instruction fine-tuned models; and 3) personality in LLM outputs can be shaped along desired dimensions to mimic specific personality profiles. We discuss application and ethical implications of the measurement and shaping method, in particular regarding responsible use of LLMs.

17 July 2019 in Current Issues in Tourism
Verified
Journal Article
Closed access
YZYing Zhang
Ying Zhang
JCJin Hooi Chan
Jin Hooi Chan
ZJZhongjuan Ji
Zhongjuan Ji
LSLuning Sun
Luning Sun
BLBernard Lane
Bernard Lane
XQXiaoguang Qi
Xiaoguang Qi
This study probes the influence of community attachment on local entrepreneurs’ perceptions of tourism’s local impacts. Six latent constructs were derived from social exchange theory and community attachment theory; 11 hypotheses were tested, using structural equation modelling, with data from 297 Taiwanese night market entrepreneurs. Significant theoretical contributions to understanding relationships between entrepreneurs and community were found: effects of community satisfaction on support for tourism were significant and fully mediated by perceived benefits. Community factors and tourist contact frequency were important in entrepreneurs’ decisions on further tourism development. Community factors showed low but significant relationships with the perceived costs of tourism, A case is made for sustainable tourism governance measures, including partnership creation, destination management systems, and visitor experience planning.

17 January 2022 in JMIR Mental Health
Verified
Journal Article
Open access
ASAnika Sierk
Anika Sierk
ETEoin Travers
Eoin Travers
MEMarcos Economides
Marcos Economides
BLBao Sheng Loe
Bao Sheng Loe
LSLuning Sun
Luning Sun
HBHeather Bolton
Heather Bolton
Background: Unmind is a workplace, digital, mental health platform with tools to help users track, maintain, and improve their mental health and well-being (MHWB). Psychological measurement plays a key role on this platform, providing users with insights on their current MHWB, the ability to track it over time, and personalized recommendations, while providing employers with aggregate information about the MHWB of their workforce. Objective: Due to the limitations of existing measures for this purpose, we aimed to develop and validate a novel well-being index for digital use, to capture symptoms of common mental health problems and key aspects of positive well-being. Methods: In Study 1A, questionnaire items were generated by clinicians and screened for face validity. In Study 1B, these items were presented to a large sample (n=1104) of UK adults, and exploratory factor analysis was used to reduce the item pool and identify coherent subscales. In Study 2, the final measure was presented to a new nationally representative UK sample (n=976), along with a battery of existing measures, with 238 participants retaking the Umind Index after 1 week. The factor structure and measurement invariance of the Unmind Index was evaluated using confirmatory factor analysis, convergent and discriminant validity by estimating correlations with existing measures, and reliability by examining internal consistency and test-retest intraclass correlations. Results: Studies 1A and 1B yielded a 26-item measure with 7 subscales: Calmness, Connection, Coping, Happiness, Health, Fulfilment, and Sleep. Study 2 showed that the Unmind Index is fitted well by a second-order factor structure, where the 7 subscales all load onto an overall MHWB factor, and established measurement invariance by age and gender. Subscale and total scores correlate well with existing mental health measures and generally diverge from personality measures. Reliability was good or excellent across all subscales. Conclusions: The Unmind Index is a robust measure of MHWB that can help to identify target areas for intervention in nonclinical users of a mental health app. We argue that there is value in measuring mental ill health and mental well-being together, rather than treating them as separate constructs.

1 April 2026 in Nature
Verified
Journal Article
Open access
PDF file
LZLexin Zhou
Lexin Zhou
LPLorenzo Pacchiardi
Lorenzo Pacchiardi
FMFernando Martínez-Plumed
Fernando Martínez-Plumed
KCKatherine M. Collins
Katherine M. Collins
YMYael Moros-Daval
Yael Moros-Daval
Jose Hernandez-OralloJose Hernandez-Orallo
Jose Hernandez-Orallo
Ensuring safe and effective use of artificial intelligence (AI) requires understanding and anticipating its performance on new tasks, from advanced scientific challenges to transformed workplace activities 1–3 . So far, benchmarking has guided progress in AI but has offered limited explanatory and predictive power for general-purpose AI systems 4–8 , attributed to limited transferability across specific tasks 9–11 . Here we introduce general scales for AI evaluation that elicit demand profiles explaining what capabilities common AI benchmarks truly measure, extract ability profiles quantifying the general strengths and limits of AI systems and robustly predict AI performance for new task instances. Our fully automated methodology builds on 18 rubrics, capturing a broad range of cognitive and intellectual demands, which place different task instances on the same general scales, illustrated on 15 large language models (LLMs) and 63 tasks. Both the demand and the ability profiles on these scales bring new insights such as construct validity through benchmark sensitivity and specificity and explain conflicting claims about whether AI has reasoning capabilities. Ultimately, high predictive power at the instance level becomes possible using the general scales, providing superior estimates over strong black-box baseline predictors, especially in out-of-distribution settings (new tasks and benchmarks). The scales, rubrics, battery, techniques and results presented here constitute a solid foundation for a science of AI evaluation, underpinning the reliable deployment of AI in the years ahead.

3 September 2021 in International Journal of Behavioral Nutrition and Physical Activity
Verified
Journal Article
Open access
PDF file
NZNan Zhou
Nan Zhou
LSLuning Sun
Luning Sun
Background: Understanding young children's eating behaviours is vital to childhood obesity prevention. However, the widely used Children's Eating Behaviour Questionnaire (CEBQ) has not been validated in Chinese young children. Thus, the present study aimed to assess the validity of the CEBQ in a Chinese urban sample of preschool children.Methods: Participants included 389 mothers with preschool children residing in Beijing, China. Confirmatory factor analysis was conducted, and measurement invariance between child genders was evaluated.Results: The modified 8-factor structure of the CEBQ exhibited acceptable model fit in our sample, and no measurement bias against any gender was observed. The associations between the CEBQ factors and child age showed that desire to drink, emotional overeating, and emotional undereating significantly decreased with age, but food responsiveness increased with age. The relation between child BMI and the CEBQ factors provided convergent validity for the CEBQ.Conclusions: Our study supported the validity of the CEBQ as a measurement tool for examining preschool children's eating behaviours in a Chinese urban sample.

14 May 2025 in Thinking Skills and Creativity
Verified
Journal Article
Open access
LSLuning Sun
Luning Sun
YYYuzhuo Yuan
Yuzhuo Yuan
YYYuan Yao
Yuan Yao
YLYanyan Li
Yanyan Li
HZHao Zhang
Hao Zhang
DSDavid Stillwell
David Stillwell