Generating Distractors for Code Completion Problems: Can LLM Assist Instructors?

While large language models (LLMs) are endowed with broad knowledge, their task-specific performance is often suboptimal. Fine-tuning LLMs with task-specific data from diverse nodes is necessary, but this data is typically safeguarded and not shared publicly due to privacy concerns. A common solution involves downstream nodes downloading the LLM locally and fine-tuning it with their proprietary data. However, owners often regard pre-trained LLMs as valuable assets and are reluctant to share them. Additionally, the significant computational resources required by LLMs make local fine-tuning impractical for many nodes. To mitigate these problems, this paper proposes CrossLM, a data-free collaborative fine-tuning framework for large and small language models. CrossLM enables resource-constrained nodes to train smaller language models (SLMs) using their private task-specific data. These SLMs are subsequently leveraged to promote the task-specific natural language generation and understanding capabilities of the LLMs. Simultaneously, the SLMs of nodes also benefit from enhancement by the fine-tuned LLMs. In this way, CrossLM avoids sharing private data and proprietary LLMs, and also reduces the resource requirements of nodes. Through extensive experiments across a range of benchmark tasks and popular language models, we demonstrate that CrossLM significantly boosts the task-specific performance of both LLMs and SLMs while preserving the generalization capabilities of LLMs.

How Can <i>IJDS</i> Authors, Reviewers, and Editors Use (and Misuse) Generative AI?

Large language models (LLMs), which are a specific subset of artificial intelligence (AI), may have the potential to revolutionize education by addressing common student misconceptions in physics. This study investigates the effectiveness of popular LLMs, such as OpenAI ChatGPT, Google Gemini, and Microsoft Copilot, in identifying and addressing misconceptions related to Newtonian mechanics in high school physics. The focus solely is on the misconception that for an elevator to move upward, the force exerted by the cable must be greater than the gravitational force acting downward on the elevator, which contradicts Newton’s first law of motion. To explore this, thirty-two experienced instructors engaged in dialogues with the LLMs, simulating learners with this misconception. Instructors evaluated the LLMs’ accuracy, personalization, and pedagogical effectiveness. The findings indicate that most instructors recognized the substantial potential of LLMs to improve student learning, particularly in addressing misconceptions through interactive dialogue, targeted questioning, and clear explanations tailored to each learner’s needs. ChatGPT ranked highest, demonstrating capabilities in delivering clear explanations, adapting to individual learners, and implementing effective teaching strategies. Google Gemini followed closely, while Microsoft Copilot was the least effective. This capability holds promise for enhancing conceptual understanding and student engagement in physics education. However, limitations were noted in the LLMs’ ability to facilitate personalized scientific discussions and utilize visual aids, such as physics diagrams, simulations, to enhance understanding. This research demonstrates the significant potential of LLMs as valuable tools for identifying and addressing misconceptions in physics education.

Large language models’ exceptional all-purpose abilities have made human-computer conversations normal, but for particular industries and verticals, they fall short of enhancing the expertise of knowledge and the timeliness of information. In order to give current information, and provide improved search capabilities, large language models need to increasingly incorporate specialist resources and databases. In this research, a model for intelligent assisted decision-making was proposed that the model incorporates knowledge from domain-specific databases and real-time data and uses large language models to offer expert tax guidance. The research proposed to overcome the limits of general-purpose language models and deliver specialized advise for tax-related inquiries by complementing large language models with domain-specific information.The results we achieve demonstrate that by offering tax advice tailored to a given situation, and the model we proposed goes beyond the validity of general large language language models. Our contribution is that not only exploring the combination of tax area and large language model, but also proposing a new effective model for government tax department to use in real life. This study highlights the potential of big language models for use in real-world professional domains and advances the field of domain-specific human-computer interaction.

Multiple-choice questions (MCQs) are ubiquitous in almost all levels of education since they are easy to administer, grade, and are a reliable format in assessments and practices.One of the most important aspects of MCQs is the distractors, i.e., incorrect options that are designed to target common errors or misconceptions among real students.To date, the task of crafting highquality distractors largely remains a labor and time-intensive process for teachers and learning content designers, which has limited scalability.In this work, we study the task of automated distractor generation in the domain of math MCQs and explore a wide variety of large language model (LLM)-based approaches, from in-context learning to fine-tuning.We conduct extensive experiments using a real-world math MCQ dataset and find that although LLMs can generate some mathematically valid distractors, they are less adept at anticipating common errors or misconceptions among real students.* As of now, Openai does not allow fine-tune GPT-4.

Introduction: Implementing board games in code can be a timeconsuming task. However, Large Language Models (LLMs) have been proven effective at generating code for domain-specific tasks with simple contextual information. Objective: We aim to investigate whether LLMs can implement digital versions of board games from rules described in natural language. This would be a step towards an LLM-assisted framework for quick board game code generation. We expect to determine the main challenges for LLMs to implement the board games, and how different approaches and models compare to one another. Methodology: We task three state-of-the-art LLMs (Claude, DeepSeek and ChatGPT) with coding a selection of 12 popular and obscure games in free-form and within Boardwalk, our proposed General Game Playing API. We anonymize the games and components to avoid evoking pre-trained LLM knowledge. The implementations are tested for playability and rule compliance. We evaluate success rate and common errors across LLMs and game popularity. Results: Our approach proves viable, with the best performing model, Claude 3.7 Sonnet, yielding 55.6% of games without any errors. While compliance with the API increases error frequency, the severity of errors is more significantly dependent on the LLM. We outline future steps for creating a framework to integrate this process, making the elaboration of board games more accessible.

Aim/Purpose: The study investigates the factors influencing the acceptance and utilisation of large language models (LLMs) (predictor variables of LLM usage), such as ChatGPT, in Learning design by instructional designers and university-teaching academics from various countries. Background: Large language models (LLMs) have exploded onto the scene, transforming the landscape of learning design. Instructional designers and university teaching academics have been overburdened with content creation for their teaching programmes, and the arrival of LLM models will help in this regard by developing more interactive content that drives student engagement and, in turn, contributes to student success. Since LLMs are a relatively new phenomenon, little is known about the factors influencing their acceptance in learning design; therefore, this research is needed, as learning design principles are the bedrock of student engagement and success. Methodology: A cross-sectional correlational quantitative study was employed. Data was collected using an online questionnaire posted on social media, including LinkedIn, from 203 instructional designers and university teaching academics. Purposive and snowball sampling methods were used to target instructional designers and university teaching academics at colleges and universities worldwide. Participants were asked to share the survey link with fellow instructional designers and university-teaching academics in their communities. The factor structure of the data was determined using exploratory factor analysis. Nonetheless, the factor structure derived from the LLMs did not entirely reflect the original configuration of the Unified Theory of Acceptance and Use of Technology (UTAUT3), as certain predictors appeared to coalesce, indicating LLMs’ unique nature in learning design. Confirmatory factor analysis was used to verify the fit of the data on the measurement model. First-order and second-order structural modelling were used to identify the structural relationships among the variables. Contribution: The study determines significant factors for the acceptance of LLMs by instructional designers and academic teaching staff in learning design, enabling possible opportunities for best practices in the field through interventions to optimize LLM usage. The study applies the technology acceptance model to the emerging LLM technology and extends the technology acceptance model by adding the trust construct as a predictor variable. Findings: The structural analysis results indicated that the ingrained LLM practices, LLM peer-driven expectations, innovative propensity towards LLM adoption, reliability and provider trust in LLMs, and ease of use and support influenced perceived LLM benefits and usage, but community standards and infrastructure had no influence. The second-order structural equation modelling indicated that perceived LLM benefits and usage and ingrained LLM habits contributed most to the learning design. Recommendations for Practitioners: Teaching academics and instructional designers must use LLMs in designing content, assessments, and interactive learning activities, and attend LLM training workshops on prompting and best practices in integrating LLMs into learning and teaching to see their benefits; hence, regular use of LLMs will then lead to trust and innovation in LLMs usage, enhancing learning design and improving student learning outcomes. Recommendation for Researchers: Researchers must use mixed methods approaches to have a deeper understanding of the factors influencing LLMs. Since habit and perceived LLM benefits and usage contributed the most variance to learning design, researchers must investigate strategies that optimise these factors in learning design, such as effective intervention strategies that can help form positive LLM habits. In addition, the findings provide researchers with a starting point for future research. Further researchers must investigate interventions that optimise the influence of personal innovativeness and trust that contributed the least variance to learning design, hence unlocking the potential of LLMs in learning design through innovation, responsible, and ethical use. Impact on Society: The use of LLMs in learning design has a high possibility of transforming education, specifically the learning design landscape. Using LLMs will free up more time for teaching academics and instructional designers so that they spend more time on higher-order thinking skill demands. Consequently, the students will be exposed to more engaging and interactive content, resulting in improved learning outcomes. Future Research: Future research must include context-derived external variables in technology acceptance models, such as levels of prompting competencies, to provide a deeper understanding of LLMs. In addition, future research must be based on the application and impact of LLMs on student engagement and success, and their attainment of 21st-century skills.

Artificial intelligence (AI) integration in medical practice has grown substantially, with physician use nearly doubling from 38% in 2023 to 68% in 2024. Recent advances in large language models (LLMs) include multimodal inputs, showing potential for medical image interpretation and clinical software integrations. This study evaluated the accuracy of two popular LLMs, Claude 3.5 Sonnet and DeepSeek R1, in interpreting glenoid diagrams using Walch glenoid classification in preoperative shoulder reconstruction applications. Test images included seven black-white Walch glenoid diagrams from Radiopedia. LLMs were accessed via Perplexity.ai without specialized medical training. LLMs were tested across multiple conversation threads with prompt instructions of varying length, ranging from 22 to 864 words for DeepSeek and 127 to 840 words for Claude. Performance differed significantly between models. DeepSeek achieved 44% accuracy (7/16), while Claude had 0% accuracy (0/16). DeepSeek showed a mild positive correlation between instruction length and response accuracy. Common errors across both LLMs included misclassifying A2 as either A1 (32%) or B2 (20%). Results highlight limitations in broadly trained LLMs’ ability to interpret even simplified medical diagrams. DeepSeek’s continuous learning feature and open-source dataset integration exhibited superior accuracy, although it was still insufficient for clinical applications. These limitations stem from LLM training data containing primarily text instead of medical images, creating pattern recognition deficiencies when interpreting visual medical information. Despite AI’s growing adoption in healthcare, this study concludes that as of February 2025, publicly available broadly trained LLMs lack the consistency and accuracy necessary for reliable medical image interpretation, emphasizing the need for specialized training before clinical implementation.

Online health information is widely available, but a substantial portion of it is inaccurate or misleading, including exaggerated, incomplete, or unverified claims. Such misinformation can significantly influence public health decisions and pose serious challenges to health care systems. With advances in artificial intelligence and natural language processing, pretrained large language models (LLMs) have shown promise in identifying and distinguishing misleading health information, although their effectiveness in this area remains underexplored. This study aimed to evaluate the performance of 4 mainstream LLMs (ChatGPT-3.5, ChatGPT-4, Ernie Bot, and iFLYTEK Spark) in the identification of online health information, providing empirical evidence for their practical application in this field. Web scraping was used to collect data from rumor-refuting websites, resulting in 2708 samples of online health information, including both true and false claims. The 4 LLMs' application programming interfaces were used for authenticity verification, with expert results as benchmarks. Model performance was evaluated using semantic similarity, accuracy, recall, F1-score, content analysis, and credibility. This study found that the 4 models performed well in identifying online health information. Among them, ChatGPT-4 achieved the highest accuracy at 87.27%, followed by Ernie Bot at 87.25%, iFLYTEK Spark at 87%, and ChatGPT-3.5 at 81.82%. Furthermore, text length and semantic similarity analysis showed that Ernie Bot had the highest similarity to expert texts, whereas ChatGPT-4 showed good overall consistency in its explanations. In addition, the credibility assessment results indicated that ChatGPT-4 provided the most reliable evaluations. Further analysis suggested that the highest misjudgment probabilities with respect to the LLMs occurred within the topics of food and maternal-infant nutrition management and nutritional science and food controversies. Overall, the research suggests that LLMs have potential in online health information identification; however, their understanding of certain specialized health topics may require further improvement. The results demonstrate that, while these models show potential in providing assistance, their performance varies significantly in terms of accuracy, semantic understanding, and cultural adaptability. The principal findings highlight the models' ability to generate accessible and context-aware explanations; however, they fall short in areas requiring specialized medical knowledge or updated data, particularly for emerging health issues and context-sensitive scenarios. Significant discrepancies were observed in the models' ability to distinguish scientifically verified knowledge from popular misconceptions and in their stability when processing complex linguistic and cultural contexts. These challenges reveal the importance of refining training methodologies to improve the models' reliability and adaptability. Future research should focus on enhancing the models' capability to manage nuanced health topics and diverse cultural and linguistic nuances, thereby facilitating their broader adoption as reliable tools for online health information identification.

The aging population presents an accomplishment for society but also poses significant challenges for governments, health care systems, and caregivers. Elevated rates of functional limitations among older adults, primarily caused by chronic conditions, necessitate adequate and safe care, including in-home settings. Traditionally, informal caregiver training has relied on verbal and written instructions. However, the advent of digital resources has introduced videos and interactive platforms, offering more accessible and effective training. Large language models (LLMs) have emerged as potential tools for personalized information delivery. While LLMs exhibit the capacity to mimic clinical reasoning and support decision-making, their potential to serve as alternatives to evidence-based professional instruction remains unexplored. We aimed to evaluate the appropriateness of home care instructions generated by LLMs (including GPTs) in comparison to a professional gold standard. Furthermore, it seeks to identify specific domains where LLMs show the most promise and where improvements are necessary to optimize their reliability for caregiver training. An observational, comparative case study evaluated 3 LLMs-GPT-3.5, GPT-4o, and Microsoft Copilot-in 10 home care scenarios. A rubric assessed the models against a reference standard (gold standard) created by health care professionals. Independent reviewers evaluated variables including specificity, clarity, and self-efficacy. In addition to comparing each LLM to the gold standard, the models were also compared against each other across all study domains to identify relative strengths and weaknesses. Statistical analyses compared LLMs performance to the gold standard to ensure consistency and validity, as well as to analyze differences between LLMs across all evaluated domains. The study revealed that while no LLM achieved the precision of the professional gold standard, GPT-4o outperformed GPT-3.5, and Copilot in specificity (4.6 vs 3.7 and 3.6), clarity (4.8 vs 4.1 and 3.9), and self-efficacy (4.6 vs 3.8 and 3.4). However, the models exhibited significant limitations, with GPT-4o and Copilot omitting relevant details in 60% (6/10) of the cases, and GPT-3.5 doing so in 80% (8/10). When compared to the gold standard, only 10% (2/20) of GPT-4o responses were rated as equally specific, 20% (4/20) included comparable practical advice, and just 5% (1/20) provided a justification as detailed as professional guidance. Furthermore, error frequency did not differ significantly across models (P=.65), though Copilot had the highest rate of incorrect information (20%, 2/10 vs 10%, 1/10 for GPT-4o and 0%, 0/0 for GPT-3.5). LLMs, particularly GPT-4o subscription-based, show potential as tools for training informal caregivers by providing tailored guidance and reducing errors. Although not yet surpassing professional instruction quality, these models offer a flexible and accessible alternative that could enhance home safety and care quality. Further research is necessary to address limitations and optimize their performance. Future implementation of LLMs may alleviate health care system burdens by reducing common caregiver errors.

To evaluate the accuracy and reasoning capabilities of large multimodal language models compared with those of neuroradiology subspecialty-trained radiologists in neuroradiology case interpretation. This experimental study used custom-made 401 radiologic quizzes derived from articles published in RadioGraphics covering neuroradiology and head and neck topics (October 2020 to February 2024). We prompted the GPT-4 Turbo with Vision (GPT-4V), GPT-4 Omni, Gemini Flash, and Claude models to provide the top three differential diagnoses with a rationale and describe examination characteristics such as imaging modality, sequence, use of contrast, image plane, and body part. The temperature was adjusted to 0 and 1 (T1). Two neuroradiologists answered the same questions. The accuracies of the large language models (LLMs) and the neuroradiologists were compared using generalized estimating equations. Three neuroradiologists assessed the rationale provided by the LLMs for their differential diagnoses using four-point scales, separately for specific lesion locations and imaging findings, and evaluated the presence of hallucinations and the overall acceptability of the responses. Top-3 accuracy (i.e., correct answers present among top-3 differential diagnoses) of LLMs ranged from 29.9% (120 of 401) to 49.4% (198 of 401, obtained with GPT-4V in the T1 setting), while radiologists achieved 80.3% (322 of 401) and 68.3% (274 of 401), respectively (P < 0.001). Regarding the rationale for differential diagnoses, GPT-4V (T1) accurately identified both the specific lesion location and imaging findings in 30.7% (123 of 401) and 12.9% (16 of 124) of cases without textual clinical history. Hallucinations occurred in 4.5% (18 of 401), and only 29.4% (118 of 401) of the LLM-generated analyses were deemed acceptable. GPT-4V (T1) demonstrated high accuracy in identifying the imaging modality (97.4% [800 of 821]) and scanned body parts (92.2% [756 of 820]). LLMs remarkably underperformed compared with neuroradiologists and showed unsatisfactory reasoning for their differential diagnoses, with performance declining further in cases without textual input of clinical history. These findings highlight the limitations of current multimodal LLMs in neuroradiological interpretation and their reliance on text input.

Large language models (LLMs) and large visual-language models (LVLMs) have exhibited near-human levels of knowledge, image comprehension, and reasoning abilities, and their performance has undergone evaluation in some healthcare domains. However, a systematic evaluation of their capabilities in cervical cytology screening has yet to be conducted. Here, we constructed CCBench, a benchmark dataset dedicated to the evaluation of LLMs and LVLMs in cervical cytology screening, and developed a GPT-based semi-automatic evaluation pipeline to assess the performance of six LLMs (GPT-4, Bard, Claude-2.0, LLaMa-2, Qwen-Max, and ERNIE-Bot-4.0) and five LVLMs (GPT-4V, Gemini, LLaVA, Qwen-VL, and ViLT) on this dataset. CCBench comprises 773 question-answer (QA) pairs and 420 visual-question-answer (VQA) triplets, making it the first dataset in cervical cytology to include both QA and VQA data. We found that LLMs and LVLMs demonstrate promising accuracy and specialization in cervical cytology screening. GPT-4 achieved the best performance on the QA dataset, with an accuracy of 70.5% for close-ended questions and average expert evaluation score of 6.9/10 for open-ended questions. On the VQA dataset, Gemini achieved the highest accuracy for close-ended questions at 67.8%, while GPT-4V attained the highest expert evaluation score of 6.1/10 for open-ended questions. Besides, LLMs and LVLMs revealed varying abilities in answering questions across different topics and difficulty levels. However, their performance remains inferior to the expertise exhibited by cytopathology professionals, and the risk of generating misinformation could lead to potential harm. Therefore, substantial improvements are required before these models can be reliably deployed in clinical practice.

Purpose This study aims to explore the integration of large language models (LLMs) and vision-language models (VLMs) in robotics, highlighting their potential benefits and the safety challenges they introduce, including robustness issues, adversarial vulnerabilities, privacy concerns and ethical implications. Design/methodology/approach This survey conducts a comprehensive analysis of the safety risks associated with LLM- and VLM-powered robotic systems. The authors review existing literature, analyze key challenges, evaluate current mitigation strategies and propose future research directions. Findings The study identifies that ensuring the safety of LLM-/VLM-driven robots requires a multi-faceted approach. While current mitigation strategies address certain risks, gaps remain in real-time monitoring, adversarial robustness and ethical safeguards. Originality/value This study offers a structured and comprehensive overview of the safety challenges in LLM-/VLM-driven robotics. It contributes to ongoing discussions by integrating technical, ethical and regulatory perspectives to guide future advancements in safe and responsible artificial intelligence-driven robotics.

Recent advancements in large language models (LLMs) have shown potential in a wide array of applications, including health care. While LLMs showed heterogeneous results across specialized medical board examinations, the performance of these models in neurology board examinations remains unexplored. To assess the performance of LLMs on neurology board-style examinations. This cross-sectional study was conducted between May 17 and May 31, 2023. The evaluation utilized a question bank approved by the American Board of Psychiatry and Neurology and was validated with a small question cohort by the European Board for Neurology. All questions were categorized into lower-order (recall, understanding) and higher-order (apply, analyze, synthesize) questions based on the Bloom taxonomy for learning and assessment. Performance by LLM ChatGPT versions 3.5 (LLM 1) and 4 (LLM 2) was assessed in relation to overall scores, question type, and topics, along with the confidence level and reproducibility of answers. Overall percentage scores of 2 LLMs. LLM 2 significantly outperformed LLM 1 by correctly answering 1662 of 1956 questions (85.0%) vs 1306 questions (66.8%) for LLM 1. Notably, LLM 2's performance was greater than the mean human score of 73.8%, effectively achieving near-passing and passing grades in the neurology board examination. LLM 2 outperformed human users in behavioral, cognitive, and psychological-related questions and demonstrated superior performance to LLM 1 in 6 categories. Both LLMs performed better on lower-order than higher-order questions, with LLM 2 excelling in both lower-order and higher-order questions. Both models consistently used confident language, even when providing incorrect answers. Reproducible answers of both LLMs were associated with a higher percentage of correct answers than inconsistent answers. Despite the absence of neurology-specific training, LLM 2 demonstrated commendable performance, whereas LLM 1 performed slightly below the human average. While higher-order cognitive tasks were more challenging for both models, LLM 2's results were equivalent to passing grades in specialized neurology examinations. These findings suggest that LLMs could have significant applications in clinical neurology and health care with further refinements.

The widespread use of online geoinformation platforms, such as Google Earth Engine (GEE), has produced numerous scripts. Extracting domain knowledge from these crowdsourced scripts supports understanding of geoprocessing workflows. Small Language Models (SLMs) are effective for semantic embedding but struggle with complex code; Large Language Models (LLMs) can summarize scripts, yet lack consistent geoscience terminology to express knowledge. In this paper, we propose Geo-CLASS, a knowledge extraction framework for geospatial analysis scripts that coordinates large and small language models. Specifically, we designed domain-specific schemas and a schema-aware prompt strategy to guide LLMs to generate and associate entity descriptions, and employed SLMs to standardize the outputs by mapping these descriptions to a constructed geoscience knowledge base. Experiments on 237 GEE scripts, selected from 295,943 scripts in total, demonstrated that our framework outperformed LLM baselines, including Llama-3, GPT-3.5 and GPT-4o. In comparison, the proposed framework improved accuracy in recognizing entities and relations by up to 31.9% and 12.0%, respectively. Ablation studies and performance analysis further confirmed the effectiveness of key components and the robustness of the framework. Geo-CLASS has the potential to enable the construction of geoprocessing modeling knowledge graphs, facilitate domain-specific reasoning and advance script generation via Retrieval-Augmented Generation (RAG).