Automating Human Tutor-Style Programming Feedback: Leveraging GPT-4 Tutor Model for Hint Generation and GPT-3.5 Student Model for Hint Validation

• URL: http://arxiv.org/abs/2310.03780v4
• Date: Tue, 6 Aug 2024 12:25:33 GMT
• Title: Automating Human Tutor-Style Programming Feedback: Leveraging GPT-4 Tutor Model for Hint Generation and GPT-3.5 Student Model for Hint Validation
• Authors: Tung Phung, Victor-Alexandru Pădurean, Anjali Singh, Christopher Brooks, José Cambronero, Sumit Gulwani, Adish Singla, Gustavo Soares,
• Abstract summary: We investigate the role of generative AI models in providing human tutor-style programming hints. Recent works have benchmarked state-of-the-art models for various feedback generation scenarios. We develop a novel technique, GPT4Hints-GPT3.5Val, to push the limits of generative AI models.
• Score: 25.317788211120362
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generative AI and large language models hold great promise in enhancing programming education by automatically generating individualized feedback for students. We investigate the role of generative AI models in providing human tutor-style programming hints to help students resolve errors in their buggy programs. Recent works have benchmarked state-of-the-art models for various feedback generation scenarios; however, their overall quality is still inferior to human tutors and not yet ready for real-world deployment. In this paper, we seek to push the limits of generative AI models toward providing high-quality programming hints and develop a novel technique, GPT4Hints-GPT3.5Val. As a first step, our technique leverages GPT-4 as a ``tutor'' model to generate hints -- it boosts the generative quality by using symbolic information of failing test cases and fixes in prompts. As a next step, our technique leverages GPT-3.5, a weaker model, as a ``student'' model to further validate the hint quality -- it performs an automatic quality validation by simulating the potential utility of providing this feedback. We show the efficacy of our technique via extensive evaluation using three real-world datasets of Python programs covering a variety of concepts ranging from basic algorithms to regular expressions and data analysis using pandas library.

Related papers

• TÜLU 3: Pushing Frontiers in Open Language Model Post-Training [94.14908801708049]
  We introduce T"ULU 3, a family of fully-open state-of-the-art post-trained models. T"ULU 3 builds on Llama 3.1 base models, achieves results surpassing the instruct versions of Llama 3.1, Qwen 2.5, Mistral, and even closed models such as GPT-4o-mini and Claude 3.5-Haiku.
  arXiv  Detail & Related papers  (2024-11-22T18:44:04Z)
• Evaluating GPT-4 at Grading Handwritten Solutions in Math Exams [48.99818550820575]
  We leverage state-of-the-art multi-modal AI models, in particular GPT-4o, to automatically grade handwritten responses to college-level math exams. Using real student responses to questions in a probability theory exam, we evaluate GPT-4o's alignment with ground-truth scores from human graders using various prompting techniques.
  arXiv  Detail & Related papers  (2024-11-07T22:51:47Z)
• Forewarned is Forearmed: Leveraging LLMs for Data Synthesis through Failure-Inducing Exploration [90.41908331897639]
  Large language models (LLMs) have significantly benefited from training on diverse, high-quality task-specific data. We present a novel approach, ReverseGen, designed to automatically generate effective training samples.
  arXiv  Detail & Related papers  (2024-10-22T06:43:28Z)
• Good things come in three: Generating SO Post Titles with Pre-Trained Models, Self Improvement and Post Ranking [5.874782446136913]
  Stack Overflow is a prominent Q and A forum, supporting developers in seeking suitable resources on programming-related matters. Having high-quality question titles is an effective means to attract developers' attention. Research has been conducted, predominantly leveraging pre-trained models to generate titles from code snippets and problem descriptions. We present FILLER as a solution to generating Stack Overflow post titles using a fine-tuned language model with self-improvement and post ranking.
  arXiv  Detail & Related papers  (2024-06-21T20:18:34Z)
• Hints-In-Browser: Benchmarking Language Models for Programming Feedback Generation [22.467879240959686]
  We benchmark language models for programming feedback generation across several performance criteria, including quality, cost, time, and data privacy. We develop a fine-tuning pipeline based on GPT-4 generated synthetic data. We showcase the efficacy of fine-tuned Llama3-8B and Phi3-3.8B 4-bit quantized models using WebLLM's in-browser inference engine.
  arXiv  Detail & Related papers  (2024-06-07T16:22:51Z)
• From GPT-3 to GPT-4: On the Evolving Efficacy of LLMs to Answer Multiple-choice Questions for Programming Classes in Higher Education [2.6626950367610402]
  We explore the evolving efficacy of three generative pre-trained transformer (GPT) models in generating answers for multiple-choice questions (MCQ) We focus on the differences in capabilities of the models prior to the release of ChatGPT (Nov '22), at the time of the release, and today (i.e., Aug '23)
  arXiv  Detail & Related papers  (2023-11-16T02:46:15Z)
• Generative Input: Towards Next-Generation Input Methods Paradigm [49.98958865125018]
  We propose a novel Generative Input paradigm named GeneInput. It uses prompts to handle all input scenarios and other intelligent auxiliary input functions, optimizing the model with user feedback to deliver personalized results. The results demonstrate that we have achieved state-of-the-art performance for the first time in the Full-mode Key-sequence to Characters(FK2C) task.
  arXiv  Detail & Related papers  (2023-11-02T12:01:29Z)
• Generative AI for Programming Education: Benchmarking ChatGPT, GPT-4, and Human Tutors [21.227955181065948]
  We systematically evaluate two models, ChatGPT (based on GPT-3.5) and GPT-4, and compare their performance with human tutors for a variety of scenarios. Our results show that GPT-4 drastically outperforms ChatGPT (based on GPT-3.5) and comes close to human tutors' performance for several scenarios.
  arXiv  Detail & Related papers  (2023-06-29T17:57:40Z)
• How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources [117.6496550359768]
  This work explores recent advances in instruction-tuning language models on a range of open instruction-following datasets. We provide a large set of instruction-tuned models from 6.7B to 65B parameters in size, trained on 12 instruction datasets. We evaluate them on their factual knowledge, reasoning, multilinguality, coding, and open-ended instruction following abilities.
  arXiv  Detail & Related papers  (2023-06-07T19:59:23Z)
• A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models [71.42197262495056]
  GPT series models have gained considerable attention due to their exceptional natural language processing capabilities. We select six representative models, comprising two GPT-3 series models and four GPT-3.5 series models. We evaluate their performance on nine natural language understanding (NLU) tasks using 21 datasets. Our experiments reveal that the overall ability of GPT series models on NLU tasks does not increase gradually as the models evolve.
  arXiv  Detail & Related papers  (2023-03-18T14:02:04Z)

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.