mlsanityData to 14 Oct 2026

Distilling ChatGPT for Explainable Automated Student Answer Assessment

arXiv 2305.12962 ↗First posted 22 May 2023cs.CLcited by 14

On the map: Knowledge distillation → Knowledge distillation for LLMs

Abstract (arXiv)

Providing explainable and faithful feedback is crucial for automated student answer assessment. In this paper, we introduce a novel framework that explores using ChatGPT, a cutting-edge large language model, for the concurrent tasks of student answer scoring and rationale generation. We identify the appropriate instructions by prompting ChatGPT with different templates to collect the rationales, where inconsistent rationales are refined to align with marking standards. The refined ChatGPT outputs enable us to fine-tune a smaller language model that simultaneously assesses student answers and provides rationales. Extensive experiments on the benchmark dataset show that the proposed method improves the overall QWK score by 11% compared to ChatGPT. Furthermore, our thorough analysis and human evaluation demonstrate that the rationales generated by our proposed method are comparable to those of ChatGPT. Our approach provides a viable solution to achieve explainable automated assessment in education. Code available at https://github.com/lijiazheng99/aera.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Placed in Knowledge distillation for LLMs, one of 12 directions in Knowledge distillation. Builds on 20 of its 36 references that are in the map. First posted on arXiv 22 May 2023.

Builds on

20 of 36 references.

References · 20

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  4. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  5. 2020Learning to summarize from human feedbackcited by 2,588
  6. 2022Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answeringcited by 1,919
  7. 2014FitNets: Hints for Thin Deep Netscited by 1,653
  8. 2019TinyBERT: Distilling BERT for Natural Language Understandingcited by 1,167
  9. 2016Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfercited by 1,077
  10. 2023A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivitycited by 894
  11. 2023Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generationcited by 819
  12. 2018Born Again Neural Networkscited by 546
8 more
  1. 2013Do Deep Nets Really Need to be Deep?cited by 474
  2. 2022Large Language Models Are Reasoning Teacherscited by 329
  3. 2016Rationalizing Neural Predictionscited by 281
  4. 2020Measuring Association Between Labels and Free-Text Rationalescited by 160
  5. 2019Interpretable Neural Predictions with Differentiable Binary Variablescited by 126
  6. 2019Rethinking Cooperative Rationalization: Introspective Extraction and Complement Controlcited by 96
  7. 2021Few-Shot Self-Rationalization with Natural Language Promptscited by 83
  8. 2018Towards Explainable NLP: A Generative Explanation Framework for Text Classificationcited by 55

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 7; 2025: 2; 2026: 3.

14 papers.

Sort:

By area:

  1. 2024A Survey on Knowledge Distillation of Large Language Modelscited by 284
  2. 2023Distilled GPT for Source Code Summarizationcited by 31
  3. 2024Rationale Behind Essay Scores: Enhancing S-LLM's Multi-Trait Essay Scoring with Rationale Generated by LLMscited by 22
  4. 2024Navigating the Landscape of Hint Generation Research: From the Past to the Futurecited by 6
  5. 2024Beyond Scores: A Modular RAG-Based System for Automatic Short Answer Scoring with Feedbackcited by 5
  6. 2024An Automated Explainable Educational Assessment System Built on LLMscited by 5
  7. 2026FeedEval: Pedagogically Aligned Evaluation of LLM-Generated Essay Feedbackcited by 4
  8. 2023An Empirical Study on Compliance with Ranking Transparency in the Software Documentation of EU Online Platformscited by 2
  9. 2024ExDDI: Explaining Drug-Drug Interaction Predictions with Natural Languagecited by 2
  10. 2024Can MLLMs generate human-like feedback in grading multimodal short answers?cited by 1
  11. 2025Concept-based Rubrics Improve LLM Formative Assessment and Data Synthesiscited by 1
  12. 2025Exploring the Utilities of the Rationales from Large Language Models to Enhance Automated Essay Scoringcited by 1
2 more
  1. 2026EDIT: Evidence-Diagnosed Intervention Training for Rule-Faithful LLM Gradingcited by 1
  2. 2026CoLearn: An Agentic Tutor that Learns its Learner in a Human--AI Co-Learning Loopcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023ChatGPT as a Math Questioner? Evaluating ChatGPT on Generating Pre-university Math Questions
  2. 2023A Systematic Study and Comprehensive Evaluation of ChatGPT on Benchmark Datasets
  3. 2026Reimagining Assessment in the Age of Generative AI: Lessons from Open-Book Exams with ChatGPT ↗
  4. 2023Automated Assessment of Students' Code Comprehension using LLMs
  5. 2024Evaluating Students' Open-ended Written Responses with LLMs: Using the RAG Framework for GPT-3.5, GPT-4, Claude-3, and Mistral-Large
  6. 2025Towards Efficient Educational Chatbots: Benchmarking RAG Frameworks
  7. 2025EduVidQA: Generating and Evaluating Long-form Answers to Student Questions based on Lecture Videos
  8. 2024The Future of Learning in the Age of Generative AI: Automated Question Generation and Assessment with Large Language Models