9 questions · 5 sources · 0 syntheses
Large Language Models
Neural networks trained on text for language understanding and generation.
Source-derived questions
Questions extracted from the papers in this topic, excluding the curated questions above.
- At which stages of the LLM life cycle, from development to deployment, can algorithmic bias enter educational applications?
- How can large language models be used to evaluate the quality of a tutor's response to a student's math error?
- How did the population of people debating AI systems change in 2023?
- How quickly did ChatGPT gain users after its November 2022 launch compared to other consumer applications?
- If the underlying model wasn't new, what made ChatGPT's interface feel different to ordinary users?
- What AI techniques, such as Bayesian Knowledge Tracing and Large Language Models, are driving improvements in adaptability and learning outcomes within tutoring systems?
- What benchmarks did GPT-4 pass that signaled a leap over previous language models?
- What technique did OpenAI use to fine-tune GPT-3.5 into a model that could hold a conversation?
- Which other major AI labs released competing language models in the months after GPT-4?
Sources
- Advancing Education through Tutoring Systems: A Systematic Literature Review
- The Life Cycle of Large Language Models: A Review of Biases in Education
- Using Large Language Models to Assess Tutors' Performance in Reacting to Students Making Math Errors
- ChatGPT launches
- GPT-4 and large language models reach mainstream deployment