Latest Articles for Education Technology

GECScore offers an efficient method to identify AI-generated text through grammar analysis.

Multicalibration enhances LLM accuracy by refining confidence scores and addressing hallucinations.

Discover methods to help AI learn continuously without forgetting past knowledge.

This framework improves text evaluation efficiency and accuracy using Large Language Models.

A new model improves AI learning by mimicking human-like consciousness.

Chameleon seamlessly merges images and text, enhancing content generation capabilities.

A study examines how students engage and perform in online learning environments.

A method enhancing the accuracy and completeness of language model answers.

A new framework enhances language model learning through interactive feedback.

Introducing ProCo, a method for better self-correction in large language models.

A new method improves the editing of dynamic 3D scenes using Gaussian shapes.

A new framework enhances AI's ability to learn through diverse challenges.

Using technology to enhance understanding of kinship in primates.

GFLean transforms natural language into formal mathematical statements efficiently.

Understanding how persona shapes interactions with conversational agents in various fields.

Examining how shared values impact trust between humans and robots.

Enhanced speech recognition for classrooms using advanced training techniques improves learning.

This study measures LLMs’ performance in complex math dialogues.

A new method improves the reliability of language models through effective retrieval.

A new approach using LLMs to create distractors with minimal human input.

This article discusses role-playing and personalization in language models.

A fresh method for training code models focusing on semantics and execution behavior.

Examining GenAI's impact on pre-service teachers in learning and teaching.

A new approach boosts language models' math abilities with speed and accuracy.

Conditional finetuning helps language models retain knowledge and reduce bias during training.

A new method enhances tracking of student knowledge over time.

Discover how recommender systems improve personalized learning experiences for students.

STARLING creates diverse text-based games to enhance RL agents' learning capabilities.

A new approach enhances accuracy and creativity in language model outputs.

Study evaluates how well LLMs reason beyond immediate context.

A new approach enhances analysis of arguments in various texts.

A new framework enhances reasoning in language models through visual sketches.

Examining the effectiveness of reasoning in large language models.

This paper investigates the False Consensus Effect in large language models.

Improving accuracy in transcribing scientific presentations through speech and visual integration.

DetectBench evaluates LLMs on their ability to detect hidden evidence in reasoning tasks.

P-Tailor customizes language models using the Big Five Personality Traits.

A new approach combines educational topics for better, personalized learning experiences.

This article discusses how AI models learn from mistakes through self-correction.

FineWeb offers 15 trillion tokens to improve language model training.