A Study on the Accuracy of Pre-Treatment Consultation Responses for Adult Orthodontic Patients Based on Large Language Models DOI Creative Commons

Chengcheng Miao,

Xiangyu Ge, Yanan Chen

и другие.

Research Square (Research Square), Год журнала: 2024, Номер unknown

Опубликована: Ноя. 13, 2024

Abstract This study compiled the 50 most common preoperative consultation questions from adult orthodontic patients through clinical observation. Responses were generated in new dialogue sessions using three large language models: Ernie Bot, ChatGPT, and Gemini. The answers assessed across five dimensions: professionalism accuracy, clarity comprehensibility of language, personalization specificity, completeness thoroughness information, empathy humanistic care. results demonstrated that Technical Accuracy(TA) was rated as reliable (44%, 78%, 74%); Clarity Comprehensibility (CC) also found (62%, 44%, 46%); Personalization Relevance (PR) Information Completeness (IC) well (58%, 70%, 70%) (74%, 82%, 66%) respectively; Empathy Human-Centeredness (EHC) considered moderately (64%, 54%, 46%). AI models showed moderate to performance terms clarity, personalization, completeness. However, they fell short dimension Therefore, it can be concluded present potential benefits for consultations. Nonetheless, given complex individual needs settings, further optimization is essential, consultations should prioritized when necessary.

Язык: Английский

The Potential Use of ChatGPT as a Sensory Evaluator of Chocolate Brownies: A Brief Case Study DOI Creative Commons
Damir D. Torrico

Foods, Год журнала: 2025, Номер 14(3), С. 464 - 464

Опубликована: Фев. 1, 2025

ChatGPT, a recently developed natural large language processing tool, has been widely explored in various fields of science and research. This study aimed to evaluate the potential use ChatGPT as sensory evaluator hypothetical formulations chocolate brownies. was prompted act an experienced taster provide detailed description characteristics for fifteen brownie grouped into three categories (standard, common ingredients replacements, uncommon replacements). Sentiment analysis, emotions/descriptors classification, correspondence analysis were conducted analyze responses. Results showed that terms “trust”, “anticipation”, “joy” most frequently expressed sentiments The valence all responses mostly positive. overall quality scores given by extremely high, range 8.5–9.5 (out 10). tended have higher positive emotions (some including worm meals fish oil) might opposite reactions with real consumers. Further research should focus on validating descriptors outcomes human panel. Additionally, future studies can explore evaluating other food products optimizing product development process.

Язык: Английский

Процитировано

0
Using LLMs in sensory service research: initial insights and perspectives DOI Creative Commons
Monika Imschloß, Marko Sarstedt, Susanne Adler

и другие.

Service Industries Journal, Год журнала: 2025, Номер unknown, С. 1 - 22

Опубликована: Март 28, 2025

Язык: Английский

Процитировано

0
A Study on the Accuracy of Pre-Treatment Consultation Responses for Adult Orthodontic Patients Based on Large Language Models DOI Creative Commons

Chengcheng Miao,

Xiangyu Ge, Yanan Chen

и другие.

Research Square (Research Square), Год журнала: 2024, Номер unknown

Опубликована: Ноя. 13, 2024

Abstract This study compiled the 50 most common preoperative consultation questions from adult orthodontic patients through clinical observation. Responses were generated in new dialogue sessions using three large language models: Ernie Bot, ChatGPT, and Gemini. The answers assessed across five dimensions: professionalism accuracy, clarity comprehensibility of language, personalization specificity, completeness thoroughness information, empathy humanistic care. results demonstrated that Technical Accuracy(TA) was rated as reliable (44%, 78%, 74%); Clarity Comprehensibility (CC) also found (62%, 44%, 46%); Personalization Relevance (PR) Information Completeness (IC) well (58%, 70%, 70%) (74%, 82%, 66%) respectively; Empathy Human-Centeredness (EHC) considered moderately (64%, 54%, 46%). AI models showed moderate to performance terms clarity, personalization, completeness. However, they fell short dimension Therefore, it can be concluded present potential benefits for consultations. Nonetheless, given complex individual needs settings, further optimization is essential, consultations should prioritized when necessary.

Язык: Английский

Процитировано

0