LLaMa-SciQ用量化模型帮大学生解科学选择题，效率提升明显。
LLaMa-SciQ: An Educational Chatbot for Answering Science MCQ
- 用人类偏好对齐微调，选LLaMa-8B作基底模型。
- 数学题准确率74.5%（GSM8k），MATH数据集30%。
- 量化后仅损失5%性能，推理更快，适合学生使用。
大型语言模型在需要数学推理的任务中表现不佳，尤其在科学类多选题（MCQ）上。为此，我们开发了LLaMa-SciQ，一个面向大学生的教育聊天机器人，用于辅助解答和理解STEM领域的多选题。首先，通过微调和对齐人类偏好优化模型；在对比Mistral-7B与LLaMa-8B后，选择后者作为基底模型，因其评估准确率更高。为进一步提升准确性，引入检索增强生成（RAG）并应用量化压缩模型，降低推理时间，提高学生可用性。在数学推理方面，LLaMa-SciQ在GSM8k数据集上达到74.5%准确率，在MATH数据集上为30%。然而，RAG并未提升性能，甚至导致下降，可能源于检索器问题或模型对上下文不熟悉。尽管如此，量化模型仅带来5%性能损失，显著提升了效率。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。