# KASER: Knowledge-Aligned Student Error Simulator for Open-Ended Coding Tasks

arXiv: https://arxiv.org/abs/2601.06633 · HTML: https://mlsanity.com/paper/2601.06633/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 56 references that are in the map.
- First posted on arXiv 10 Jan 2026.

## Builds on (most cited first, 18 of 18)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [CodeBLEU: a Method for Automatic Evaluation of Code Synthesis](https://mlsanity.com/paper/2009.10297/) (2020)
- [Meta-learning via Language Model In-context Tuning](https://mlsanity.com/paper/2110.07814/) (2021)
- [Exploring Knowledge Tracing in Tutor-Student Dialogues using LLMs](https://mlsanity.com/paper/2409.16490/) (2024)
- [SMART: Simulated Students Aligned with Item Response Theory for Question Difficulty Prediction](https://mlsanity.com/paper/2507.05129/) (2025)
- [Synthesizing Tasks for Block-based Programming](https://mlsanity.com/paper/2006.16913/) (2020)
- [Exploring applications of deep reinforcement learning for real-world autonomous driving systems](https://mlsanity.com/paper/1901.01536/) (2019)
- [Psychometric Alignment: Capturing Human Knowledge Distributions via Language Models](https://mlsanity.com/paper/2407.15645/) (2024)
- [Reasoning and Sampling-Augmented MCQ Difficulty Prediction via LLMs](https://mlsanity.com/paper/2503.08551/) (2025)
- [Automated Knowledge Concept Annotation and Question Representation Learning for Knowledge Tracing](https://mlsanity.com/paper/2410.01727/) (2024)
- [Modeling Student Learning with 3.8 Million Program Traces](https://mlsanity.com/paper/2510.05056/) (2025)
- [From {Solution Synthesis} to {Student Attempt Synthesis} for Block-Based Visual Programming Tasks](https://mlsanity.com/paper/2205.01265/) (2022)
- [Test Case-Informed Knowledge Tracing for Open-ended Coding Tasks](https://mlsanity.com/paper/2410.10829/) (2024)
- [Agent Performing Autonomous Stock Trading under Good and Bad Situations](https://mlsanity.com/paper/2306.03985/) (2023)

## Built on by (most cited first, 7 of 7)

- [Letting Tutor Personas Speak Up for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization](https://mlsanity.com/paper/2602.07639/) (2026)
- [Who Am I? History-Aware Profiles for Student Simulation in Tutoring Dialogues](https://mlsanity.com/paper/2605.30051/) (2026)
- [Teaching Language Models How to Code Like Learners: Conversational Serialization for Student Simulation](https://mlsanity.com/paper/2604.10720/) (2026)
- [Using LLMs for Knowledge Component-level Correctness Labeling in Open-ended Coding Problems](https://mlsanity.com/paper/2602.17542/) (2026)
- [CodeGENCAT: Generative Computerized Adaptive Testing for Open-ended Coding Problems](https://mlsanity.com/paper/2602.20020/) (2026)
- [Exploring the Effectiveness of Using LLMs for Automated Assessment of Student Self Explanations in Programming Education](https://mlsanity.com/paper/2605.21614/) (2026)
- [From Learner Behavior to Reusable Skills for Effective and Efficient Learner Simulation](https://mlsanity.com/paper/2609.37157/) (2026)

## Abstract (arXiv)

Open-ended tasks, such as coding problems that are common in computer science education, provide detailed insights into student knowledge. However, training large language models (LLMs) to simulate and predict possible student errors in their responses to these problems can be challenging: they often suffer from mode collapse and fail to fully capture the diversity in syntax, style, and solution approach in student responses. In this work, we present KASER (Knowledge-Aligned Student Error Simulator), a novel approach that aligns errors with student knowledge. We propose a training method based on reinforcement learning using a hybrid reward that reflects three aspects of student code prediction: i) code similarity to the ground-truth, ii) error matching, and iii) code prediction diversity. On two real-world datasets, we perform two levels of evaluation and show that: At the per-student-problem pair level, our method outperforms baselines on code and error prediction; at the per-problem level, our method outperforms baselines on error coverage and simulated code diversity.