AI-TA: Towards an Intelligent Question-Answer Teaching Assistant using Open-Source LLMs

• URL: http://arxiv.org/abs/2311.02775v3
• Date: Mon, 18 Dec 2023 23:23:06 GMT
• Title: AI-TA: Towards an Intelligent Question-Answer Teaching Assistant using Open-Source LLMs
• Authors: Yann Hicke, Anmol Agarwal, Qianou Ma, Paul Denny
• Abstract summary: We introduce an innovative solution that leverages open-source Large Language Models (LLMs) to ensure data privacy. Our approach combines augmentation techniques such as retrieval augmented generation (RAG), supervised fine-tuning (SFT), and learning from human preferences data. This work paves the way for the development of AI-TA, an intelligent QA assistant customizable for courses with an online QA platform.
• Score: 2.6513660158945727
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Responding to the thousands of student questions on online QA platforms each semester has a considerable human cost, particularly in computing courses with rapidly growing enrollments. To address the challenges of scalable and intelligent question-answering (QA), we introduce an innovative solution that leverages open-source Large Language Models (LLMs) from the LLaMA-2 family to ensure data privacy. Our approach combines augmentation techniques such as retrieval augmented generation (RAG), supervised fine-tuning (SFT), and learning from human preferences data using Direct Preference Optimization (DPO). Through extensive experimentation on a Piazza dataset from an introductory CS course, comprising 10,000 QA pairs and 1,500 pairs of preference data, we demonstrate a significant 30% improvement in the quality of answers, with RAG being a particularly impactful addition. Our contributions include the development of a novel architecture for educational QA, extensive evaluations of LLM performance utilizing both human assessments and LLM-based metrics, and insights into the challenges and future directions of educational data processing. This work paves the way for the development of AI-TA, an intelligent QA assistant customizable for courses with an online QA platform

Related papers

• From MOOC to MAIC: Reshaping Online Teaching and Learning through LLM-driven Agents [78.15899922698631]
  MAIC (Massive AI-empowered Course) is a new form of online education that leverages LLM-driven multi-agent systems to construct an AI-augmented classroom. We conduct preliminary experiments at Tsinghua University, one of China's leading universities.
  arXiv  Detail & Related papers  (2024-09-05T13:22:51Z)
• SIaM: Self-Improving Code-Assisted Mathematical Reasoning of Large Language Models [54.78329741186446]
  We propose a novel paradigm that uses a code-based critic model to guide steps including question-code data construction, quality control, and complementary evaluation. Experiments across both in-domain and out-of-domain benchmarks in English and Chinese demonstrate the effectiveness of the proposed paradigm.
  arXiv  Detail & Related papers  (2024-08-28T06:33:03Z)
• A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models [71.25225058845324]
  Large Language Models (LLMs) have demonstrated revolutionary abilities in language understanding and generation. Retrieval-Augmented Generation (RAG) can offer reliable and up-to-date external knowledge. RA-LLMs have emerged to harness external and authoritative knowledge bases, rather than relying on the model's internal knowledge.
  arXiv  Detail & Related papers  (2024-05-10T02:48:45Z)
• Automatic Question-Answer Generation for Long-Tail Knowledge [65.11554185687258]
  We propose an automatic approach to generate specialized QA datasets for tail entities. We conduct extensive experiments by employing pretrained LLMs on our newly generated long-tail QA datasets.
  arXiv  Detail & Related papers  (2024-03-03T03:06:31Z)
• QACP: An Annotated Question Answering Dataset for Assisting Chinese Python Programming Learners [10.90557801193242]
  This paper proposes a new Chinese question-and-answer dataset for Python learners. It is designed to enhance the effectiveness and quality of online programming education.
  arXiv  Detail & Related papers  (2024-01-30T13:11:23Z)
• Federated Fine-Tuning of LLMs on the Very Edge: The Good, the Bad, the Ugly [62.473245910234304]
  This paper takes a hardware-centric approach to explore how Large Language Models can be brought to modern edge computing systems. We provide a micro-level hardware benchmark, compare the model FLOP utilization to a state-of-the-art data center GPU, and study the network utilization in realistic conditions.
  arXiv  Detail & Related papers  (2023-10-04T20:27:20Z)
• Modern Question Answering Datasets and Benchmarks: A Survey [5.026863544662493]
  Question Answering (QA) is one of the most important natural language processing (NLP) tasks. It aims using NLP technologies to generate a corresponding answer to a given question based on the massive unstructured corpus. In this paper, we investigate influential QA datasets that have been released in the era of deep learning.
  arXiv  Detail & Related papers  (2022-06-30T05:53:56Z)
• Results and Insights from Diagnostic Questions: The NeurIPS 2020 Education Challenge [40.96530220202453]
  This competition concerns educational diagnostic questions, which are pedagogically effective, multiple-choice questions (MCQs) We seek to answer the question: how can we use data on hundreds of millions of answers to MCQs to drive automatic personalized learning in large-scale learning scenarios? We report on our NeurIPS competition in which nearly 400 teams submitted approximately 4000 submissions, with encouragingly diverse and effective approaches to each of our tasks.
  arXiv  Detail & Related papers  (2021-04-08T20:09:58Z)
• Template-Based Question Generation from Retrieved Sentences for Improved Unsupervised Question Answering [98.48363619128108]
  We propose an unsupervised approach to training QA models with generated pseudo-training data. We show that generating questions for QA training by applying a simple template on a related, retrieved sentence rather than the original context sentence improves downstream QA performance.
  arXiv  Detail & Related papers  (2020-04-24T17:57:45Z)
• Educational Question Mining At Scale: Prediction, Analysis and Personalization [35.42197158180065]
  We propose a framework for mining insights from educational questions at scale. We utilize the state-of-the-art Bayesian deep learning method, in particular partial variational auto-encoders (p-VAE) We apply our proposed framework to a real-world dataset with tens of thousands of questions and tens of millions of answers from an online education platform.
  arXiv  Detail & Related papers  (2020-03-12T19:07:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.