ParaStudent: Generating and Evaluating Realistic Student Code by Teaching LLMs to Struggle

• URL: http://arxiv.org/abs/2507.12674v2
• Date: Fri, 18 Jul 2025 01:02:16 GMT
• Title: ParaStudent: Generating and Evaluating Realistic Student Code by Teaching LLMs to Struggle
• Abstract summary: Large Language Models (LLMs) have shown strong performance on programming tasks, but can they generate student-like code like real students?<n>We present ParaStudent, a systematic study of LLM-based "student-like" code generation in an introductory programming course setting.
• Score: 24.691302820912888
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) have shown strong performance on programming tasks, but can they generate student-like code like real students - imperfect, iterative, and stylistically diverse? We present ParaStudent, a systematic study of LLM-based "student-like" code generation in an introductory programming course setting. Using a dataset of timestamped student submissions across multiple semesters, we design low- and high-resolution experiments to model student progress and evaluate code outputs along semantic, functional, and stylistic dimensions. Our results show that fine-tuning significantly improves alignment with real student trajectories and captures error patterns, incremental improvements, and stylistic variations more faithfully. This study shows that modeling realistic student code requires capturing learning dynamics through context-aware generation, temporal modeling, and multi-dimensional evaluation. Code for experiments and evaluation is available at https://github.com/mmiroyan/ParaStudent.

Related papers

• Gumbel Machine: Counterfactual Student Writing Generation via Gumbel Noise Steering [41.340472784619756]
  An ideal learning demonstration is a counterfactual version of the student work, an improved version that is still similar to their own.<n>Existing automated approaches for counterfactual text generation using Large Language Models (LLMs) result in domain-specific systems that are difficult to translate into practical applications.<n>We present the Gumbel Machine, a flexible, modular approach to generating counterfactuals that leverages LLM instruction-following capabilities while encouraging similarity to a reference factual text.
  arXiv  Detail & Related papers  (2026-05-26T16:27:07Z)
• Teaching Language Models How to Code Like Learners: Conversational Serialization for Student Simulation [4.361813083295904]
  We propose a method for training open-weight artificial programming learners using authentic student process data.<n>Our approach serializes temporal log traces into a conversational format, representing each student's problem-solving process.<n>Student code submissions and environment feedback, such as test outcomes, grades, and error traces, form alternating conversational turns.
  arXiv  Detail & Related papers  (2026-04-12T16:38:42Z)
• Readability-Robust Code Summarization via Meta Curriculum Learning [53.44612630063336]
  In the real world, code is often poorly structured or obfuscated, significantly degrading model performance.<n>We propose RoFTCodeSum, a novel fine-tuning method that enhances the robustness of code summarization against poorly readable code.
  arXiv  Detail & Related papers  (2026-01-09T02:38:24Z)
• Understanding Specification-Driven Code Generation with LLMs: An Empirical Study Design [2.687678248171195]
  Large Language Models (LLMs) are increasingly integrated into software development, yet their behavior in structured, specification-driven processes remains poorly understood.<n>This paper presents an empirical study design using CURRANTE, a Visual Studio Code extension that enables a human-in-the-loop workflow for LLM-assisted code generation.<n>The study aims to analyze how human intervention in specification and test refinement influences the quality and dynamics of LLM-generated code.
  arXiv  Detail & Related papers  (2026-01-07T12:46:57Z)
• UCO: A Multi-Turn Interactive Reinforcement Learning Method for Adaptive Teaching with Large Language Models [59.693733170193944]
  Large language models (LLMs) are shifting from answer providers to intelligent tutors in educational settings.<n>Recent reinforcement learning approaches address this limitation but face two critical challenges.<n>We propose the Unidirectional Cognitive Optimization (UCO) method to address these challenges.
  arXiv  Detail & Related papers  (2025-11-12T01:27:02Z)
• Modeling Student Learning with 3.8 Million Program Traces [52.153493498021895]
  We introduce a dataset of over 3.8 million programming reasoning traces from users of Pencil Code.<n>We find that models trained on real traces are stronger at modeling diverse student behavior.<n>We show that we can help students recover from mistakes by steering code generation models to identify a sequence of edits that will result in more correct code.
  arXiv  Detail & Related papers  (2025-10-06T17:37:17Z)
• Embracing Imperfection: Simulating Students with Diverse Cognitive Levels Using LLM-based Agents [36.704574105201864]
  Large language models (LLMs) are revolutionizing education, with LLM-based agents playing a key role in simulating student behavior.<n>A major challenge in student simulation is modeling the diverse learning patterns of students at various cognitive levels.
  arXiv  Detail & Related papers  (2025-05-26T13:48:49Z)
• Learning Code-Edit Embedding to Model Student Debugging Behavior [2.1485350418225244]
  We propose an encoder-decoder-based model that learns meaningful code-edit embeddings between consecutive student code submissions.<n>It enables personalized next-step code suggestions that maintain the student's coding style while improving test case correctness.
  arXiv  Detail & Related papers  (2025-02-26T18:54:39Z)
• Classroom Simulacra: Building Contextual Student Generative Agents in Online Education for Learning Behavioral Simulation [10.209326669619273]
  We run a 6-week education workshop from N = 60 students to collect fine-grained data using a custom built online education system.<n>We propose a transferable iterative reflection (TIR) module that augments both prompting-based and finetuning-based large language models.
  arXiv  Detail & Related papers  (2025-02-04T23:42:52Z)
• DataEnvGym: Data Generation Agents in Teacher Environments with Student Feedback [62.235925602004535]
  DataEnvGym is a testbed of teacher environments for data generation agents.<n>It frames data generation as a sequential decision-making task, involving an agent and a data generation engine.<n>Students are iteratively trained and evaluated on generated data, and their feedback is reported to the agent after each iteration.
  arXiv  Detail & Related papers  (2024-10-08T17:20:37Z)
• Toward In-Context Teaching: Adapting Examples to Students' Misconceptions [54.82965010592045]
  We introduce a suite of models and evaluation methods we call AdapT. AToM is a new probabilistic model for adaptive teaching that jointly infers students' past beliefs and optimize for the correctness of future beliefs. Our results highlight both the difficulty of the adaptive teaching task and the potential of learned adaptive models for solving it.
  arXiv  Detail & Related papers  (2024-05-07T17:05:27Z)
• Code Representation Learning At Scale [75.04686476303436]
  We fuel code representation learning with a vast amount of code data via a two-stage pretraining scheme. We first train the encoders via a mix that leverages both randomness in masking language modeling and the structure aspect of programming language. We then enhance the representations via contrastive learning with hard negative and hard positive constructed in an unsupervised manner.
  arXiv  Detail & Related papers  (2024-02-02T22:19:15Z)
• Large Language Models for In-Context Student Modeling: Synthesizing Student's Behavior in Visual Programming [29.65988680948297]
  We explore the application of large language models (LLMs) for in-context student modeling in open-ended learning domains. We introduce a novel framework, LLM for Student Synthesis (LLM-SS), that leverages LLMs for a student's behavior. We instantiate several methods based on LLM-SS framework and evaluate them using an existing benchmark, StudentSyn, for student attempt synthesis in a visual programming domain.
  arXiv  Detail & Related papers  (2023-10-15T12:56:13Z)
• LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning [64.55001982176226]
  LIBERO is a novel benchmark of lifelong learning for robot manipulation. We focus on how to efficiently transfer declarative knowledge, procedural knowledge, or the mixture of both. We develop an extendible procedural generation pipeline that can in principle generate infinitely many tasks.
  arXiv  Detail & Related papers  (2023-06-05T23:32:26Z)
• Multi-granulariy Time-based Transformer for Knowledge Tracing [9.788039182463768]
  We leverage students historical data, including their past test scores, to create a personalized model for each student. We then use these models to predict their future performance on a given test.
  arXiv  Detail & Related papers  (2023-04-11T14:46:38Z)
• Enhancing Semantic Code Search with Multimodal Contrastive Learning and Soft Data Augmentation [50.14232079160476]
  We propose a new approach with multimodal contrastive learning and soft data augmentation for code search. We conduct extensive experiments to evaluate the effectiveness of our approach on a large-scale dataset with six programming languages.
  arXiv  Detail & Related papers  (2022-04-07T08:49:27Z)
• Learning Multi-Objective Curricula for Deep Reinforcement Learning [55.27879754113767]
  Various automatic curriculum learning (ACL) methods have been proposed to improve the sample efficiency and final performance of deep reinforcement learning (DRL) In this paper, we propose a unified automatic curriculum learning framework to create multi-objective but coherent curricula. In addition to existing hand-designed curricula paradigms, we further design a flexible memory mechanism to learn an abstract curriculum.
  arXiv  Detail & Related papers  (2021-10-06T19:30:25Z)

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.