The Ability of ChatGPT in Paraphrasing Texts and Reducing Plagiarism: A Descriptive Analysis.

Background: The introduction of ChatGPT by OpenAI has garnered significant attention. Among its capabilities, paraphrasing stands out. Objective: This study aims to investigate the satisfactory levels of plagiarism in the paraphrased text produced by this chatbot. Methods: Three texts of varying lengths were presented to ChatGPT. ChatGPT was then instructed to paraphrase the provided texts using five different prompts. In the subsequent stage of the study, the texts were divided into separate paragraphs, and ChatGPT was requested to paraphrase each paragraph individually. Lastly, in the third stage, ChatGPT was asked to paraphrase the texts it had previously generated. Results: The average plagiarism rate in the texts generated by ChatGPT was 45% (SD 10%). ChatGPT exhibited a substantial reduction in plagiarism for the provided texts (mean difference -0.51, 95% CI -0.54 to -0.48; P<.001). Furthermore, when comparing the second attempt with the initial attempt, a significant decrease in the plagiarism rate was observed (mean difference -0.06, 95% CI -0.08 to -0.03; P<.001). The number of paragraphs in the texts demonstrated a noteworthy association with the percentage of plagiarism, with texts consisting of a single paragraph exhibiting the lowest plagiarism rate (P<.001). Conclusions: Although ChatGPT demonstrates a notable reduction of plagiarism within texts, the existing levels of plagiarism remain relatively high. This underscores a crucial caution for researchers when incorporating this chatbot into their work.

ClickSAM: Fine-tuning Segment Anything Model using click prompts for ultrasound image segmentation.

The newly released Segment Anything Model (SAM) is a popular tool used in image processing due to its superior segmentation accuracy, variety of input prompts, training capabilities, and efficient model design. However, its current model is trained on a diverse dataset not tailored to medical images, particularly ultrasound images. Ultrasound images tend to have a lot of noise, making it difficult to segment out important structures. In this project, we developed ClickSAM, which fine-tunes the Segment Anything Model using click prompts for ultrasound images. ClickSAM has two stages of training: the first stage is trained on single-click prompts centered in the ground-truth contours, and the second stage focuses on improving the model performance through additional positive and negative click prompts. By comparing the first stage's predictions to the ground-truth masks, true positive, false positive, and false negative segments are calculated. Positive clicks are generated using the true positive and false negative segments, and negative clicks are generated using the false positive segments. The Centroidal Voronoi Tessellation algorithm is then employed to collect positive and negative click prompts in each segment that are used to enhance the model performance during the second stage of training. With click-train methods, ClickSAM exhibits superior performance compared to other existing models for ultrasound image segmentation.

Structure-aware diffusion for low-dose CT imaging.

Reducing the radiation dose leads to the X-ray computed tomography (CT) images suffering from heavy noise and artifacts, which inevitably interferes with the subsequent clinic diagnostic and analysis. Leading works have explored diffusion models for low-dose CT imaging to avoid the structure degeneration and blurring effects of previous deep denoising models. However, most of them always begin their generative processes with Gaussian noise, which has little or no structure priors of the clean data distribution, thereby leading to long-time inference and unpleasant reconstruction quality. To alleviate these problems, this paper presents a Structure-Aware Diffusion model (SAD), an end-to-end self-guided learning framework for high-fidelity CT image reconstruction. First, SAD builds a nonlinear diffusion bridge between clean and degraded data distributions, which could directly learn the implicit physical degradation prior from observed measurements. Second, SAD integrates the prompt learning mechanism and implicit neural representation into the diffusion process, where rich and diverse structure representations extracted by degraded inputs are exploited as prompts, which provides global and local structure priors, to guide CT image reconstruction. Finally, we devise an efficient self-guided diffusion architecture using an iterative updated strategy, which further refines structural prompts during each generative step to drive finer image reconstruction. Extensive experiments on AAPM-Mayo and LoDoPaB-CT datasets demonstrate that our SAD could achieve superior performance in terms of noise removal, structure preservation, and blind-dose generalization, with few generative steps, even one step only.

ChatGPT prompts for generating multiple-choice questions in medical education and evidence on their validity: a literature review.

ChatGPT's role in creating multiple-choice questions (MCQs) is growing but the validity of these artificial-intelligence-generated questions is unclear. This literature review was conducted to address the urgent need for understanding the application of ChatGPT in generating MCQs for medical education. Following the database search and screening of 1920 studies, we found 23 relevant studies. We extracted the prompts for MCQ generation and assessed the validity evidence of MCQs. The findings showed that prompts varied, including referencing specific exam styles and adopting specific personas, which align with recommended prompt engineering tactics. The validity evidence covered various domains, showing mixed accuracy rates, with some studies indicating comparable quality to human-written questions, and others highlighting differences in difficulty and discrimination levels, alongside a significant reduction in question creation time. Despite its efficiency, we highlight the necessity of careful review and suggest a need for further research to optimize the use of ChatGPT in question generation. Main messages  Ensure high-quality outputs by utilizing well-designed prompts; medical educators should prioritize the use of detailed, clear ChatGPT prompts when generating MCQs. Avoid using ChatGPT-generated MCQs directly in examinations without thorough review to prevent inaccuracies and ensure relevance. Leverage ChatGPT's potential to streamline the test development process, enhancing efficiency without compromising quality.

Tailored Prompting to Improve Adherence to Image-Based Dietary Assessment: Mixed Methods Study.

Background: Accurately assessing an individual's diet is vital in the management of personal nutrition and in the study of the effect of diet on health. Despite its importance, the tools available for dietary assessment remain either too imprecise, expensive, or burdensome for clinical or research use. Image-based methods offer a potential new tool to improve the reliability and accessibility of dietary assessment. Though promising, image-based methods are sensitive to adherence, as images cannot be captured from meals that have already been consumed. Adherence to image-based methods may be improved with appropriately timed prompting via text message. Objective: This study aimed to quantitatively examine the effect of prompt timing on adherence to an image-based dietary record and qualitatively explore the participant experience of dietary assessment in order to inform the design of a novel image-based dietary assessment tool. Methods: This study used a randomized crossover design to examine the intraindividual effect of 3 prompt settings on the number of images captured in an image-based dietary record. The prompt settings were control, where no prompts were sent; standard, where prompts were sent at 7:15 AM, 11:15 AM, and 5:15 PM for every participant; and tailored, where prompt timing was tailored to habitual meal times for each participant. Participants completed a text-based dietary record at baseline to determine the timing of tailored prompts. Participants were randomized to 1 of 6 study sequences, each with a unique order of the 3 prompt settings, with each 3-day image-based dietary record separated by a washout period of at least 7 days. The qualitative component comprised semistructured interviews and questionnaires exploring the experience of dietary assessment. Results: A total of 37 people were recruited, and 30 participants (11 male, 19 female; mean age 30, SD 10.8 years), completed all image-based dietary records. The image rate increased by 0.83 images per day in the standard setting compared to control (P=.23) and increased by 1.78 images per day in the tailored setting compared to control (P≤.001). We found that 13/21 (62%) of participants preferred to use the image-based dietary record versus the text-based dietary record but reported method-specific challenges with each method, particularly the inability to record via an image after a meal had been consumed. Conclusions: Tailored prompting improves adherence to image-based dietary assessment. Future image-based dietary assessment tools should use tailored prompting and offer both image-based and written input options to improve record completeness.

An Empirical Evaluation of Prompting Strategies for Large Language Models in Zero-Shot Clinical Natural Language Processing: Algorithm Development and Validation Study.

BACKGROUND: Large language models (LLMs) have shown remarkable capabilities in natural language processing (NLP), especially in domains where labeled data are scarce or expensive, such as the clinical domain. However, to unlock the clinical knowledge hidden in these LLMs, we need to design effective prompts that can guide them to perform specific clinical NLP tasks without any task-specific training data. This is known as in-context learning, which is an art and science that requires understanding the strengths and weaknesses of different LLMs and prompt engineering approaches. OBJECTIVE: The objective of this study is to assess the effectiveness of various prompt engineering techniques, including 2 newly introduced types-heuristic and ensemble prompts, for zero-shot and few-shot clinical information extraction using pretrained language models. METHODS: This comprehensive experimental study evaluated different prompt types (simple prefix, simple cloze, chain of thought, anticipatory, heuristic, and ensemble) across 5 clinical NLP tasks: clinical sense disambiguation, biomedical evidence extraction, coreference resolution, medication status extraction, and medication attribute extraction. The performance of these prompts was assessed using 3 state-of-the-art language models: GPT-3.5 (OpenAI), Gemini (Google), and LLaMA-2 (Meta). The study contrasted zero-shot with few-shot prompting and explored the effectiveness of ensemble approaches. RESULTS: The study revealed that task-specific prompt tailoring is vital for the high performance of LLMs for zero-shot clinical NLP. In clinical sense disambiguation, GPT-3.5 achieved an accuracy of 0.96 with heuristic prompts and 0.94 in biomedical evidence extraction. Heuristic prompts, alongside chain of thought prompts, were highly effective across tasks. Few-shot prompting improved performance in complex scenarios, and ensemble approaches capitalized on multiple prompt strengths. GPT-3.5 consistently outperformed Gemini and LLaMA-2 across tasks and prompt types. CONCLUSIONS: This study provides a rigorous evaluation of prompt engineering methodologies and introduces innovative techniques for clinical information extraction, demonstrating the potential of in-context learning in the clinical domain. These findings offer clear guidelines for future prompt-based clinical NLP research, facilitating engagement by non-NLP experts in clinical NLP advancements. To the best of our knowledge, this is one of the first works on the empirical evaluation of different prompt engineering approaches for clinical NLP in this era of generative artificial intelligence, and we hope that it will inspire and inform future research in this area.

The Effect of Explicit Suicide Language in Engagement With a Suicide Prevention Search Page Help-Seeking Prompt: Nonrandomized Trial.

BACKGROUND: Given that signage, messaging, and advertisements (ads) are the gateway to many interventions in suicide prevention, it is important that we understand what type of messaging works best for whom. OBJECTIVE: We investigated whether explicitly mentioning suicide increases engagement using internet ads by investigating engagement with campaigns with different categories of keywords searched, which may reflect different cognitive states. METHODS: We ran a 2-arm study Australia-wide, with or without ads featuring explicit suicide wording. We analyzed whether there were differences in engagement for campaigns with explicit and nonexplicit ads for low-risk (distressed but not explicitly suicidal), high-risk (explicitly suicidal), and help-seeking for suicide keywords. RESULTS: Our analyses revealed that having explicit wording has opposite effects, depending on the search terms used: explicit wording reduced the engagement rate for individuals searching for low-risk keywords but increased engagement for those using high-risk keywords. CONCLUSIONS: The findings suggest that individuals who are aware of their suicidality respond better to campaigns that explicitly use the word "suicide." We found that individuals who search for low-risk keywords also respond to explicit ads, suggesting that some individuals who are experiencing suicidality search for low-risk keywords.

Long-Term Effectiveness of a Multi-Strategy Choice Architecture Intervention in Increasing Healthy Food Choices of High-School Students From Online Canteens (Click & Crunch High Schools): Cluster Randomized Controlled Trial.

BACKGROUND: School canteens are a recommended setting to influence adolescent nutrition due to their scope to improve student food choices. Online lunch ordering systems ("online canteens") are increasingly used and represent attractive infrastructure to implement choice architecture interventions that nudge users toward healthier food choices. A recent cluster randomized controlled trial demonstrated the short-term effectiveness (2-month follow-up) of a choice architecture intervention to increase the healthiness of foods purchased by high school students from online canteens. However, there is little evidence regarding the long-term effectiveness of choice architecture interventions targeting adolescent food purchases, particularly those delivered online. OBJECTIVE: This study aimed to determine the long-term effectiveness of a multi-strategy choice architecture intervention embedded within online canteen infrastructure in high schools at a 15-month follow-up. METHODS: A cluster randomized controlled trial was undertaken with 1331 students (from 9 high schools) in New South Wales, Australia. Schools were randomized to receive the automated choice architecture intervention (including menu labeling, positioning, feedback, and prompting strategies) or the control (standard online ordering). The foods purchased were classified according to the New South Wales Healthy Canteen strategy as either "everyday," "occasional," or "should not be sold." Primary outcomes were the average proportion of "everyday," "occasional," and "should not be sold" items purchased per student. Secondary outcomes were the mean energy, saturated fat, sugar, and sodium content of purchases. Outcomes were assessed using routine data collected by the online canteen. RESULTS: From baseline to 15-month follow-up, on average, students in the intervention group ordered significantly more "everyday" items (+11.5%, 95% CI 7.3% to 15.6%; P<.001), and significantly fewer "occasional" (-5.4%, 95% CI -9.4% to -1.5%; P=.007) and "should not be sold" items (-6%, 95% CI -9.1% to -2.9%; P<.001), relative to controls. There were no between-group differences over time in the mean energy, saturated fat, sugar, or sodium content of lunch orders. CONCLUSIONS: Given their longer-term effectiveness, choice architecture interventions delivered via online canteens may represent a promising option for policy makers to support healthy eating among high school students. TRIAL REGISTRATION: Australian Clinical Trials ACTRN12620001338954, https://anzctr.org.au/Trial/Registration/TrialReview.aspx?id=380546 ; Open Science Framework osf.io/h8zfr, https://osf.io/h8zfr/.

On the Efficacy of Accuracy Prompts Across Partisan Lines: An Adversarial Collaboration.

The spread of misinformation is a pressing societal challenge. Prior work shows that shifting attention to accuracy increases the quality of people's news-sharing decisions. However, researchers disagree on whether accuracy-prompt interventions work for U.S. Republicans/conservatives and whether partisanship moderates the effect. In this preregistered adversarial collaboration, we tested this question using a multiverse meta-analysis (k = 21; N = 27,828). In all 70 models, accuracy prompts improved sharing discernment among Republicans/conservatives. We observed significant partisan moderation for single-headline "evaluation" treatments (a critical test for one research team) such that the effect was stronger among Democrats than Republicans. However, this moderation was not consistently robust across different operationalizations of ideology/partisanship, exclusion criteria, or treatment type. Overall, we observed significant partisan moderation in 50% of specifications (all of which were considered critical for the other team). We discuss the conditions under which moderation is observed and offer interpretations.

Comparing the impact of simple and educational point-of-decision messages on nutritional choice outcomes.

Emerging evidence suggests that point-of-decision messages may be an effective way to promote healthy food choices. Previous studies show improvements in overall nutritional quality, as well as increases in underconsumed food categories, such as fruits and vegetables, and underconsumed nutrients of public health concern, like dietary fiber. However, there have been multiple approaches used for delivering point-of-decision messages, including very brief messages that remind individuals to consider health during choice, as well as longer messages providing educational information about health benefits. While both approaches have demonstrated positive impacts on outcomes, there is no comparative evidence of the messages' effectiveness. In this study, we examine the impact of four messages on two nutritional attributes of cereals selected in a two-round pre- and post-message breakfast cereal choice exercise with numerous (n = 33) breakfast cereals available. Data were collected via an online survey of adult US residents recruited from the Prolific consumer panel. Three of the messages were simple reminder messages (taste, health, fiber), while there was additionally a longer fiber-focused messaging detailing the health benefits of fiber. Findings show that the simple messages outperformed the longer educational message, though there were some trade-offs between general health and fiber messages. The simple dietary fiber-focused message resulted in significantly higher dietary fiber content in cereals chosen than in any other messaging condition, while the general health message did not result in significantly higher measures of nutritional quality than the simple fiber message. The results of the study suggest that simpler messages may be more effective at increasing the nutritional quality of food choices. Additionally, messages focused on specific nutrients lead to significantly greater increases in the content of those nutrients.

A quality improvement approach to improving recognition of Maori tamariki (children) and assessing barriers to culturally responsive care in a paediatric ward setting.

BACKGROUND: Health inequity persists in Aotearoa (New Zealand) and internationally amongst most indigenous peoples. To address these health inequities, countries need to contend with the ramifications of entrenched historical, cultural and systemic failures. Within Aotearoa part of the solution to rectifying persistent health inequities lies in shifting everyday healthcare practices towards a more culturally responsive, patient-centred approach that utilises Maori knowledge and principles. Although the need for culturally responsive services in healthcare settings is clearly evident, most practitioners struggle with the challenge of creating a culturally safe environment. Further to these challenges, there are issues related to accurate recognition of ethnicity within the time constraints of an overwrought hospital environment. Within this environment, the correct identification of ethnicity is a fundamental step in the process of moving towards culturally responsive and more inclusive care. METHOD: The research was concerned with indigenous Maori patients being consistently and correctly identified so that they might receive culturally appropriate interaction and treatment. The research specifically focused on the impact of introducing a customised sticker prompt on the front cover of clinical notes of Maori tamariki (children) to assist with correct ethnicity identification. Surveys were conducted on the paediatric ward over a 3-week period, prior to and during the intervention to evaluate the effect of the customised stickers. This study sought to (1) assess the efficacy of a sticker to improve recognition of Maori tamariki (children), (2) examine key barriers to identifying ethnicity and (3) identify wider impacts of a sticker prompt on clinical practice. RESULTS: Results showed wide ranging positive impacts on clinical practice and culturally responsive care. Sixty-four per cent of participants indicated that the stickers were a useful tool to improve identification of Maori tamariki. Respondents reported increased accuracy of identifying patients by ethnicity, as well as improved awareness of existing ethnicity documentation, and increased engagement regarding cultural needs and ethnicity. CONCLUSIONS: This study identified that sticker prompts are a useful tool for healthcare workers to improve recognition and awareness of ethnicity and to increase dialogue around cultural needs. The stickers led to increased consideration of the wider elements of holistic wellbeing and therefore improved culturally responsive care for Maori tamariki.

Exploring Whether the Electronic Optimization of Routine Health Assessments Can Increase Testing for Sexually Transmitted Infections and Provider Acceptability at an Aboriginal Community Controlled Health Service: Mixed Methods Evaluation.

BACKGROUND: In the context of a syphilis outbreak in neighboring states, a multifaceted systems change to increase testing for sexually transmitted infections (STIs) among young Aboriginal people aged 15 to 29 years was implemented at an Aboriginal Community Controlled Health Service (ACCHS) in New South Wales, Australia. The components included electronic medical record prompts and automated pathology test sets to increase STI testing in annual routine health assessments, the credentialing of nurses and Aboriginal health practitioners to conduct STI tests independently, pathology request forms presigned by a physician, and improved data reporting. OBJECTIVE: We aimed to determine whether the systems change increased the integration of STI testing into routine health assessments by clinicians between April 2019 and March 2020, the inclusion of syphilis tests in STI testing, and STI testing uptake overall. We also explored the understandings of factors contributing to the acceptability and normalization of the systems change among staff. METHODS: We used a mixed methods design to evaluate the effectiveness and acceptability of the systems change implemented in 2019. We calculated the annual proportion of health assessments that included tests for chlamydia, gonorrhea, and syphilis, as well as an internal control (blood glucose level). We conducted an interrupted time series analysis of quarterly proportions 24 months before and 12 months after the systems change and in-depth semistructured interviews with ACCHS staff using normalization process theory. RESULTS: Among 2461 patients, the annual proportion of health assessments that included any STI test increased from 16% (38/237) in the first year of the study period to 42.9% (94/219) after the implementation of the systems change. There was an immediate and large increase when the systems change occurred (coefficient=0.22; P=.003) with no decline for 12 months thereafter. The increase was greater for male individuals, with no change for the internal control. Qualitative data indicated that nurse- and Aboriginal health practitioner-led testing and presigned pathology forms proved more difficult to normalize than electronic prompts and shortcuts. The interviews identified that staff understood the modifications to have encouraged cultural change around the role of sexual health care in routine practice. CONCLUSIONS: This study provides evidence for the first time that optimizing health assessments electronically is an effective and acceptable strategy to increase and sustain clinician integration and the completeness of STI testing among young Aboriginal people attending an ACCHS. Future strategies should focus on increasing the uptake of health assessments and promote whole-of-service engagement and accountability.

Exploratory mixed methods analysis of self-authored content from participants in a digital alcohol intervention trial.

BACKGROUND: Digital interventions readily permit data capture of participant engagement with them. If future interventions are intended to be more interactive, tailored, or a useful resource offered to users, it may be valuable to examine such data. One module available in a digital alcohol intervention recently tested in a randomised control trial offered participants the opportunity to self-author prompts that were sent to them by a text message at a time of their choosing. This study thus aimed to evaluate these self-authored prompts to increase knowledge on how individuals negotiate behaviour change and assess whether intervention content can be improved in the future. METHODS: The self-authored prompts were evaluated qualitatively using a combination of content and thematic analysis. The identified themes and subcategories are exemplified using anonymized quotes, and the frequency that each identified theme was coded for among the prompts was calculated. Associations between baseline characteristics and the odds of authoring a prompt at all, as well as a prompt within each theme, were investigated using logistic regression. RESULTS: Five themes were identified (Encouragement Style, Level of Awareness, Reminders of reasons to reduce/quit, Strategies to reduce/quit, and Timescale), all with several subcategories. The prompts module was more likely to be used by women and older individuals, as well as those for whom reducing alcohol consumption was perceived as important, or who felt they had the know-how to do so. Participants who had immediate access to the support tool (intervention group) were more than twice as likely to author a prompt (OR = 2.36; probability of association > 99%) compared to those with 4-month delayed access (control group). CONCLUSIONS: Individuals who engaged with the prompts module showed evidence of using the information provided in the support tool in an active way, with several showing goal setting and making plans to change their drinking behaviour. Individuals also used this opportunity to remind themselves of personal and specific reasons they wanted to change their drinking, as well as to encourage themselves to do so.

Prompt Engineering as an Important Emerging Skill for Medical Professionals: Tutorial.

Prompt engineering is a relatively new field of research that refers to the practice of designing, refining, and implementing prompts or instructions that guide the output of large language models (LLMs) to help in various tasks. With the emergence of LLMs, the most popular one being ChatGPT that has attracted the attention of over a 100 million users in only 2 months, artificial intelligence (AI), especially generative AI, has become accessible for the masses. This is an unprecedented paradigm shift not only because of the use of AI becoming more widespread but also due to the possible implications of LLMs in health care. As more patients and medical professionals use AI-based tools, LLMs being the most popular representatives of that group, it seems inevitable to address the challenge to improve this skill. This paper summarizes the current state of research about prompt engineering and, at the same time, aims at providing practical recommendations for the wide range of health care professionals to improve their interactions with LLMs.

Open-ended initial invitations are particularly helpful in eliciting forensically relevant information from child witnesses.

BACKGROUND: Open-ended prompting is an essential tool for interviewers to elicit evidentiary information from children reporting abuse. To date, no research has examined whether different types of open-ended prompts elicit details with differing levels of forensic relevance. OBJECTIVE: To examine interviewers' use of three open-ended prompt subtypes (initial invitations, breadth prompts, and depth prompts) and compare the forensic relevance of the information elicited by each. PARTICIPANTS AND SETTING: Transcripts of field interviews conducted by 53 police interviewers with children aged 6- to 16-years alleging abuse were examined. METHODS: In each transcript, initial invitations, breadth prompts, and depth prompts were identified, and the child's response was parsed into clauses. Clauses were classified according to their forensic relevance: essential to the charge (i.e., a key point of proof or element of the offence), relevant to the offending (i.e., what occurred before, during, or after an incident but not an essential detail), context (i.e., background information), irrelevant to the charge, no information provided, or repeated information already provided earlier. RESULTS: Interviewers posed fewer initial invitations than breadth and depth prompts, p < .001, ηp2 = 0.58. Initial invitations elicited higher proportions of essential and relevant clauses than breadth and depth prompts; depth prompts further elicited higher proportions of essential clauses than breadth prompts, ps ≤ 0.001. We found few effects of children's age. CONCLUSIONS: Initial invitations are a particularly useful subtype of open-ended prompt for interviewers to elicit details that are legislatively essential for prosecution of crimes from children of all ages.

The Impact of Prompts and Feedback on the Performance during Multi-Session Self-Regulated Learning in the Hypermedia Environment.

The hypermedia environment is among the most prevalent contemporary self-regulated learning (SRL) environments; however, methods for improving the effectiveness of students' multi-session SRL in such environments remain under discussion. In this study, two experiments were conducted to explore whether and how prompts and feedback benefit performance during multi-session SRL in a hypermedia learning environment. A total of 76 senior students participated in Experiment 1, which used a mixed 2 (prompting condition: prompt, no prompt) × 2 (feedback condition: feedback, no feedback) × 2 (learning session: Session 1 and Session 2) design to explore the effects of prompting and feedback on the multi-session learning process in a hypermedia environment. The results indicated that, in learning Session 1, performance in the prompt condition was significantly better than in the unprompted condition, with or without feedback; in learning Session 2, participants in the prompt condition with feedback performed significantly better than those in the other three conditions. Students in the group with a prompt and feedback had the most accurate meta-comprehension absolute accuracy in both learning sessions. Experiment 2 recruited 94 secondary school students to further explore whether the combination of prompts and different types of feedback led to different learning outcomes according to the division of feedback timing. A mixed 2 (prompt condition: prompt, no prompt) × 3 (feedback condition: delayed feedback, immediate feedback, no feedback) × 2 (learning session: Session 1 and Session 2) design was used. The results indicated that, in learning Session 1, the prompt condition outperformed the unprompted condition with or without feedback; in learning Session 2, students with prompted delayed feedback outperformed the other five conditions. We also found that although there was no significant difference in meta-comprehension monitoring accuracy between delayed and immediate feedback, both groups performed significantly better than those in the no feedback condition. These results suggest that the combination of prompts and feedback in hypermedia environments facilitates student performance better than prompts or feedback alone; this improvement may be related to the correction of poor internal student feedback.

Prompt Engineering with ChatGPT: A Guide for Academic Writers.

Prompt engineering is a relatively new discipline that refers to the practice of developing and optimizing prompts to effectively utilize large language models, particularly in natural language processing tasks. However, not many writers and researchers are familiar about this discipline. Hence, in this paper, I aim to highlight the significance of prompt engineering for academic writers and researchers, particularly the fledgling, in the rapidly evolving world of artificial intelligence. I also discuss the concepts of prompt engineering, large language models, and the techniques and pitfalls of writing prompts. Here, I contend that by acquiring prompt engineering skills, academic writers can navigate the changing landscape and leverage large language models to enhance their writing process. As artificial intelligence continues to advance and penetrate the arena of academic writing, prompt engineering equips writers and researchers with the essential skills to effectively harness the power of language models. This enables them to confidently explore new opportunities, enhance their writing endeavors, and remain at the forefront of utilizing cutting-edge technologies in their academic pursuits.

Metacognitive prompts and numerical ordinality in solving word problems: An eye-tracking study.

BACKGROUND: The ability to translate concrete manipulatives into abstract mathematical formulas can aid in the solving of mathematical word problems among students, and metacognitive prompts play a significant role in enhancing this process. AIMS: Based on the concept of semantic congruence, we explored the effects of metacognitive prompts and numerical ordinality on information searching and cognitive processing, throughout the process of solving mathematical word problems among primary school students in China. SAMPLE: Participants included 73 primary school students (38 boys and 35 girls) with normal or corrected visual acuity. METHODS: This study was based on a 2 (prompt information: no-prompt, metacognitive-prompt) × 2 (number attribute: cardinal number, ordinal number) mixed experimental design. We analysed multiple eye-movement indices, such as fixation duration, saccadic amplitude, and pupil size, since they pertained to the areas of interest. RESULTS: When solving both types of problems, pupil sizes were significantly smaller under the metacognitive-prompt condition compared with the no-prompt condition, and shorter dwell time for specific sentences, conditional on metacognitive prompts, indicated the optimization of the presented algorithm. Additionally, the levels of fixation durations and saccadic amplitudes were significantly higher when solving ordinal number word problems compared with solving ordinal number problems, indicating that primary school students were less efficient in reading and faced increased levels of difficulty when solving ordinal number problems. CONCLUSIONS: The results indicate that for Chinese upper-grade primary school students, cognitive load was lower in the metacognitive prompting condition and when solving cardinal problems, and higher when solving ordinal problems.

Virtual Reality Training of Social Skills in Adults with Autism Spectrum Disorder: An Examination of Acceptability, Usability, User Experience, Social Skills, and Executive Functions.

Poor social skills in autism spectrum disorder (ASD) are associated with reduced independence in daily life. Current interventions for improving the social skills of individuals with ASD fail to represent the complexity of real-life social settings and situations. Virtual reality (VR) may facilitate social skills training in social environments and situations similar to those in real life; however, more research is needed to elucidate aspects such as the acceptability, usability, and user experience of VR systems in ASD. Twenty-five participants with ASD attended a neuropsychological evaluation and three sessions of VR social skills training, which incorporated five social scenarios with three difficulty levels. Participants reported high acceptability, system usability, and user experience. Significant correlations were observed between performance in social scenarios, self-reports, and executive functions. Working memory and planning ability were significant predictors of the functionality level in ASD and the VR system's perceived usability, respectively. Yet, performance in social scenarios was the best predictor of usability, acceptability, and functionality level. Planning ability substantially predicted performance in social scenarios, suggesting an implication in social skills. Immersive VR social skills training in individuals with ASD appears to be an appropriate service, but an errorless approach that is adaptive to the individual's needs should be preferred.