Large Language Models in Education and Information Discovery

The field of large language models (LLMs) is moving towards greater integration in education and information discovery, with a focus on addressing challenges such as academic integrity, student over-reliance, and functional fixedness. Researchers are exploring the benefits and drawbacks of LLMs in software engineering education, including their potential to enhance learning experiences and provide personalized tutoring. The role of LLMs in information discovery and synthesis is also being investigated, with studies comparing their effectiveness to traditional search engines. Noteworthy papers include: Catch Me if You Search, which found that integrating web search results into LLMs can help detect hallucinations. Trapped by Expectations, which introduced a typology for user intents in chat search and highlighted the importance of mitigating functional fixedness to support more creative and analytical use of LLMs.

Sources

Integrating LLMs in Software Engineering Education: Motivators, Demotivators, and a Roadmap Towards a Framework for Finnish Higher Education Institutes

Catch Me if You Search: When Contextual Web Search Results Affect the Detection of Hallucinations

Trapped by Expectations: Functional Fixedness in LLM-Enabled Chat Search

Exploring undercurrents of learning tensions in an LLM-enhanced landscape: A student-centered qualitative perspective on LLM vs Search

Built with on top of