large language models

Subjectless Self-Referential Collapse: The Perception Paradox and Repeater Deadlock of Large Language Models in Closed-Loop Iterations

摘要 (Abstract) 当前人工智能研究广泛依赖大语言模型(LLMs)的自我反思与多智能体辩论,试图通过闭环交互实现“否定之否定”的螺旋式进化。本研究通过零数据集、零算力的实证观察,发现并命名了一种大模型的根本性系统缺陷:无主体自指坍塌(Subjectless Self-Referential Collapse, SSR-Collapse)。实验表明,当大模型在一个缺乏外部物理锚定的闭环中(...

Multimodal deep learning architecture for gym exercise recognition and real-time posture error detection using LSTM and RAG-based expert chatbot

The growing popularity of home fitness has led to an increase in home-based fitness training. Still, the lack of supervision by a trained professional has resulted in improper form, thereby increasing the risk of injury during exercise. Automated computer vision systems have also been developed to monitor exercise, but...

A multifactor model for assessing programming knowledge based on the synchronization of AI analytics and expert evaluation

Introduction The widespread adoption of generative AI tools has created new methodological challenges for the validity of assessment in higher education. If a neural network can write code, how can a student's actual knowledge be assessed objectively? This study proposes a multifactor AI-assisted assessment model for t...

Developing and validating the attitudes toward large language models scale

Architectural and Governance Approaches to Controlling Large Language Model Costs in Healthcare Information Systems

Large language models are entering healthcare information systems through documentation, retrieval, summarization, multimodal interpretation, and administrative workflows. Their operating costs depend on more than unit pricing because repeated context transfers, unnecessary model calls, retries, long outputs, and reuse...

Multimodal LLMs for Leprosy Diagnostic Support: Evaluating Performance and Healthcare Professionals’ Trust and Acceptance

Leprosy remains a major public health challenge in high-burden regions, where its clinical similarity to other dermatoses and reliance on clinical assessment can contribute to delayed diagnosis. Although multimodal Large Language Models (LLMs) have shown potential for dermatological decision support, their performance...

Reimagining Inquiry Through AI: Emerging Technologies for Scalable Complex Problem-Solving

Abstract This emerging technology report examines the design, development, and implementation of an artificial intelligence (AI)d chatbot to support inquiry-based learning within a K–12 capstone context. Grounded in the increasing emphasis on ill-structured problem-solving aligned with contemporary educational standard...

Large Language Models Are More Sycophantic in Chinese Than in English

AI sycophancy has emerged as a prominent concern in human–AI interaction, as large language models (LLMs) may unduly affirm users’ beliefs or actions rather than provide independent assessments. Such behavior may vary across languages because language can cue culturally patterned norms of social interaction. Prior work...

Codevelopment, Implementation, and Evaluation of an AI-powered Conversational Interface for Tobacco Cessation: Protocol for a Single-Group Pre-Post Study

Background Despite several efforts to expand tobacco cessation services through tobacco cessation centers (TCCs) and quit lines, key operational challenges still persist. Recently, AI-based digital interventions have shown promise globally for smoking cessation; however, they remain underused in tobacco cessation strat...

QI Meets AI—Implications and Opportunities for Laboratory Medicine

Abstract The integration of artificial intelligence (AI) and large language models into healthcare is reshaping quality improvement (QI), creating unprecedented opportunities while introducing new risks that require dedicated governance frameworks and professional competencies. AI-enabled QI has significant implication...

Evaluating Gemma 3 27B for local undergraduate physics tutoring

Abstract Physics education research has developed a range of student-centered approaches that emphasize conceptual understanding and problem solving, creating interest in whether large language models (LLMs) can provide complementary, on-demand tutoring support. Locally deployable models are particularly relevant for i...

Boosting AI-based speech performance assessment through pairwise comparative scoring of crowd data

Open-ended performance assessments can capture intellectual status that is difficult to measure using highly constrained response formats. However, their practical use is limited by the difficulty of obtaining reliable, scalable, and interpretable scores. Recent advances in large language models provide new opportuniti...