Privacy-Preserving Information Extraction for Ethical Case Studies in Machine Learning Using ChatGLM-LtMP

Electronics, Journal Year: 2025, Volume and Issue: 14(7), P. 1352 - 1352

Published: March 28, 2025

Ensuring privacy protection in machine learning is crucial for handling sensitive information, particularly ethical case studies within computer engineering. Traditional information extraction methods often expose private data to risks such as membership inference and reconstruction attacks, compromising confidentiality. To address these concerns, we propose ChatGLM-LtMP, a privacy-preserving framework that integrates Least-to-Most Prompting P-Tuning v2 structured secure retrieval. By employing controlled prompting mechanisms, our approach minimizes exposure while maintaining high accuracy (93.71%), outperforming baseline models. Additionally, construct knowledge graph using the Neo4j 4.4 database integrate LangChain 0.2 case-based intelligent question answering. This enables interpretable of data, making it suitable applications scenarios. The proposed method advances extraction, safeguarding cases from potential attacks automated environments.

Language: Английский

Bridging LMS and Generative AI: Dynamic Course Content Integration (DCCI) for Connecting LLMs to Course Content – The Ask ME Assistant

Research Square (Research Square), Journal Year: 2025, Volume and Issue: unknown

Published: March 31, 2025

The integration of Large Language Models (LLMs) with Learning Management Systems (LMSs) has the potential to enhance task automation and accessibility in education. However, hallucination where LLMs generate inaccurate or misleading information remains a significant challenge. This study introduces Dynamic Course Content Integration (DCCI) mechanism, which dynamically retrieves integrates course content curriculum from Canvas LMS into LLM-powered assistant, Ask ME. By employing prompt engineering structure retrieved within LLM’s context window, DCCI ensures accuracy, relevance, contextual alignment, mitigating hallucination. To evaluate DCCI’s effectiveness, ME’s usability, broader student perceptions AI education, mixed-methods approach was employed, incorporating user satisfaction ratings structured survey. Results pilot indicate high (4.614/5), students recognizing ability provide timely contextually relevant responses for both administrative course-related inquiries. Additionally, majority agreed that reduced platform-switching, improving engagement, comprehension. AI’s role reducing classroom hesitation fostering self-directed learning intellectual curiosity also highlighted. Despite these benefits positive perception tools, concerns emerged regarding over-reliance on AI, accuracy limitations, ethical issues such as plagiarism student-teacher interaction. These findings emphasize need strategic implementation, safeguards, pedagogical framework prioritizes human-AI collaboration over substitution. contributes AI-enhanced education by demonstrating how context-aware retrieval mechanisms like improve LLM reliability educational engagement while ensuring responsible integration.

Language: Английский

Exploring How AI Literacy and Self-Regulated Learning Relate to Student Writing Performance and Well-Being in Generative AI-Supported Higher Education

Behavioral Sciences, Journal Year: 2025, Volume and Issue: 15(5), P. 705 - 705

Published: May 20, 2025

The integration of generative artificial intelligence (GAI) into higher education is transforming students’ learning processes, academic performance, and psychological well-being. Despite the increasing adoption GAI tools, mechanisms through which AI literacy self-regulated (SRL) relate to their emotional experiences remain underexplored. This study investigates how SRL are associated with writing performance digital well-being among university students in GAI-supported contexts. A survey was administered 257 from universities China, structural equation modeling used examine hypothesized relationships. Results show that both significantly positively predict having a stronger effect. Moreover, shows positive association GAI-driven well-being, serving as partial mediator this relationship. These findings suggest fostering technological competencies effective strategies may support outcomes while supporting AI-enriched educational environments. By integrating unified model, contributes growing body research on offers practical implications for cultivating balanced sustainable age GAI.

Language: Английский