Summary of Llama-sciq: An Educational Chatbot For Answering Science Mcq, by Marc-antoine Allard et al.
LLaMa-SciQ: An Educational Chatbot for Answering Science MCQ
by Marc-Antoine Allard, Matin Ansaripour, Maria Yuffa, Paul Teiletche
First submitted to arxiv on: 25 Sep 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: None
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 abstract discusses the development of an educational chatbot called LLaMa-SciQ, designed to assist college students in solving and understanding multiple-choice questions (MCQs) in STEM fields. The chatbot is based on a Large Language Model (LLM) and fine-tuned to align with human preferences. The authors compare the performance of two models, Mistral-7B and LLaMa-8B, and select LLaMa-8B as the base model due to its higher evaluation accuracy. To enhance accuracy, the authors implement Retrieval-Augmented Generation (RAG) and apply quantization to compress the model, reducing inference time and increasing accessibility for students. The chatbot achieves 74.5% accuracy on the GSM8k dataset and 30% on the MATH dataset for mathematical reasoning tasks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary LLaMa-SciQ is a new educational chatbot designed to help college students solve math problems. It’s based on a special type of artificial intelligence called Large Language Models. The chatbot was trained to think like humans and understand what they want to learn. It can even give explanations for the answers! In tests, LLaMa-SciQ did really well, especially with simple math questions. |
Keywords
» Artificial intelligence » Inference » Large language model » Llama » Quantization » Rag » Retrieval augmented generation
