# A Risk-Adaptive and Evidence-Constrained Framework for Generative AI Feedback in Programming Education

arXiv: https://arxiv.org/abs/2609.29874 · HTML: https://mlsanity.com/paper/2609.29874/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 34 references that are in the map.
- First posted on arXiv 24 Sep 2026.

## Builds on (most cited first, 12 of 12)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [Automatic Generation of Programming Exercises and Code Explanations using Large Language Models](https://mlsanity.com/paper/2206.11861/) (2022)
- [Knowledge Tracing: A Survey](https://mlsanity.com/paper/2201.06953/) (2022)
- [Using Large Language Models to Enhance Programming Error Messages](https://mlsanity.com/paper/2210.11630/) (2022)
- [Exploring How Multiple Levels of GPT-Generated Programming Hints Support or Disappoint Novices](https://mlsanity.com/paper/2404.02213/) (2024)
- [Evaluating Language Models for Generating and Judging Programming Feedback](https://mlsanity.com/paper/2407.04873/) (2024)
- [You're (Not) My Type -- Can LLMs Generate Feedback of Specific Types for Introductory Programming Tasks?](https://mlsanity.com/paper/2412.03516/) (2024)

## Abstract (arXiv)

Generative artificial intelligence can turn learning analytics into personalized support, but feedback systems must decide when to intervene, which evidence to use, and how much assistance to provide. We developed a risk-adaptive, evidence-constrained framework for introductory programming using 2993 failed-submission states from 215 students. Student-disjoint models predicted persistent failure and related outcomes; four matched feedback conditions were generated for 136 cases; and calibrated risk informed capacity-limited intervention policies. The validation-selected logistic regression model achieved a test precision-recall area under the curve of 0.550 and a receiver operating characteristic area under the curve of 0.681. Broader student histories improved prediction of unmodified resubmission. After standardized repair and evidence gating, 519 of 544 newly generated messages contained all required components. A fixed-threshold sequential policy selected 17.8% of eligible test states and captured 25.2% of observed persistent failures. These findings support an evidence-gated progressive assistance strategy: calibrated risk guides intervention timing, recorded evidence constrains feedback content, and assistance progresses from self-checks to localized hints when warranted. The framework connects prediction, decision-making, and grounded generation while keeping their evaluation outcomes distinct.