The field of large language models (LLMs) is rapidly evolving, with a focus on improving their reliability, transparency, and educational applications. Recent developments have centered around reducing hallucinations and enhancing the quality of LLM-generated content, particularly in educational settings. Researchers have proposed innovative approaches, such as multi-agent systems and LLM-as-a-Judge techniques, to evaluate and improve the reliability of LLM-generated scaffolds for self-regulated learning. Additionally, there is a growing emphasis on developing large-scale datasets, like SCALEFeedback, to support the development of generalizable methods for automatic generation of effective and responsible educational feedback. Noteworthy papers in this area include 'Towards Reliable Generative AI-Driven Scaffolding' and 'SCALEFeedback: A Large-Scale Dataset of Synthetic Computer Science Assignments for LLM-generated Educational Feedback Research', which demonstrate significant advancements in LLM-based educational feedback and scaffolding systems. Furthermore, studies like 'Highlight All the Phrases: Enhancing LLM Transparency through Visual Factuality Indicators' highlight the importance of transparency and factuality in LLM outputs, proposing novel design strategies for communicating factuality scores to users.
Advancements in Large Language Models for Education and Transparency
Sources
Towards Reliable Generative AI-Driven Scaffolding: Reducing Hallucinations and Enhancing Quality in Self-Regulated Learning Support
SCALEFeedback: A Large-Scale Dataset of Synthetic Computer Science Assignments for LLM-generated Educational Feedback Research
Dean of LLM Tutors: Exploring Comprehensive and Automated Evaluation of LLM-generated Educational Feedback via LLM Feedback Evaluators
Highlight All the Phrases: Enhancing LLM Transparency through Visual Factuality Indicators
Conversational DNA: A New Visual Language for Understanding Dialogue Structure in Human and AI
Word Clouds as Common Voices: LLM-Assisted Visualization of Participant-Weighted Themes in Qualitative Interviews
MLego: Interactive and Scalable Topic Exploration Through Model Reuse
Real-time News Story Identification
Assessing the Quality of AI-Generated Exams: A Large-Scale Field Study
LLM-as-a-Supervisor: Mistaken Therapeutic Behaviors Trigger Targeted Supervisory Feedback
Adoption of Explainable Natural Language Processing: Perspectives from Industry and Academia on Practices and Challenges
Thematic and Task-Based Categorization of K-12 GenAI Usages with Hierarchical Topic Modeling
From Answers to Questions: EQGBench for Evaluating LLMs' Educational Question Generation
Evaluation of GPT-based large language generative AI models as study aids for the national licensure examination for registered dietitians in Japan
Beyond Self-Regulated Learning Processes: Unveiling Hidden Tactics in Generative AI-Assisted Writing
When Explainability Meets Privacy: An Investigation at the Intersection of Post-hoc Explainability and Differential Privacy in the Context of Natural Language Processing