LLaMa-SciQ: An Educational Chatbot for Answering Science MCQ
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916410845822976 |
|---|---|
| author | Allard, Marc-Antoine Ansaripour, Matin Yuffa, Maria Teiletche, Paul |
| author_facet | Allard, Marc-Antoine Ansaripour, Matin Yuffa, Maria Teiletche, Paul |
| contents | Large Language Models (LLMs) often struggle with tasks requiring mathematical reasoning, particularly multiple-choice questions (MCQs). To address this issue, we developed LLaMa-SciQ, an educational chatbot designed to assist college students in solving and understanding MCQs in STEM fields. We begin by fine-tuning and aligning the models to human preferences. After comparing the performance of Mistral-7B and LLaMa-8B, we selected the latter as the base model due to its higher evaluation accuracy. To further enhance accuracy, we implement Retrieval-Augmented Generation (RAG) and apply quantization to compress the model, reducing inference time and increasing accessibility for students. For mathematical reasoning, LLaMa-SciQ achieved 74.5% accuracy on the GSM8k dataset and 30% on the MATH dataset. However, RAG does not improve performance and even reduces it, likely due to retriever issues or the model's unfamiliarity with context. Despite this, the quantized model shows only a 5% loss in performance, demonstrating significant efficiency improvements. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_16779 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LLaMa-SciQ: An Educational Chatbot for Answering Science MCQ Allard, Marc-Antoine Ansaripour, Matin Yuffa, Maria Teiletche, Paul Artificial Intelligence Large Language Models (LLMs) often struggle with tasks requiring mathematical reasoning, particularly multiple-choice questions (MCQs). To address this issue, we developed LLaMa-SciQ, an educational chatbot designed to assist college students in solving and understanding MCQs in STEM fields. We begin by fine-tuning and aligning the models to human preferences. After comparing the performance of Mistral-7B and LLaMa-8B, we selected the latter as the base model due to its higher evaluation accuracy. To further enhance accuracy, we implement Retrieval-Augmented Generation (RAG) and apply quantization to compress the model, reducing inference time and increasing accessibility for students. For mathematical reasoning, LLaMa-SciQ achieved 74.5% accuracy on the GSM8k dataset and 30% on the MATH dataset. However, RAG does not improve performance and even reduces it, likely due to retriever issues or the model's unfamiliarity with context. Despite this, the quantized model shows only a 5% loss in performance, demonstrating significant efficiency improvements. |
| title | LLaMa-SciQ: An Educational Chatbot for Answering Science MCQ |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2409.16779 |