Summary of Supporting Student Decisions on Learning Recommendations: An Llm-based Chatbot with Knowledge Graph Contextualization For Conversational Explainability and Mentoring, by Hasan Abu-rasheed et al.
Supporting Student Decisions on Learning Recommendations: An LLM-Based Chatbot with Knowledge Graph Contextualization for Conversational Explainability and Mentoring
by Hasan Abu-Rasheed, Mohamad Hussam Abdulsalam, Christian Weber, Madjid Fathi
First submitted to arxiv on: 16 Jan 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Computation and Language (cs.CL); Human-Computer Interaction (cs.HC)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed approach utilizes chatbots as mediators to leverage large language models (LLMs) for explaining learning recommendations. By controlling the LLM’s output through defined prompts, the system regulates the quality of explanations while reducing potential risks. The chatbot-based system supports students in understanding personalized learning pathways and can be connected to human mentors for guidance. This proof-of-concept demonstrates the potential benefits and limitations of incorporating chatbots into conversational explainability. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Imagine you’re trying to learn something new, but you don’t understand why a certain recommendation was made for you. A chatbot can help by having a conversation with you, kind of like talking to a friend or mentor. The problem is that current chatbots aren’t good enough to replace a human mentor. So, this paper proposes an idea: using chatbots as mediators between students and large language models (LLMs). The LLMs generate explanations, but the chatbot helps control what they say to make sure it’s helpful and accurate. This can help students understand why certain recommendations were made and how they can work together with a human mentor to achieve their goals. |
