# SWIM: Student Writing Simulation via Proficiency-Conditioned Generation

arXiv: https://arxiv.org/abs/2609.03215 · HTML: https://mlsanity.com/paper/2609.03215/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 45 references that are in the map.
- First posted on arXiv 2 Sep 2026.

## Builds on (most cited first, 19 of 19)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [A Long Way to Go: Investigating Length Correlations in RLHF](https://mlsanity.com/paper/2310.03716/) (2023)
- [Benchmarking Generation and Evaluation Capabilities of Large Language Models for Instruction Controllable Summarization](https://mlsanity.com/paper/2311.09184/) (2023)
- [Generative Students: Using LLM-Simulated Student Profiles to Support Question Item Evaluation](https://mlsanity.com/paper/2405.11591/) (2024)
- [On the Use of BERT for Automated Essay Scoring: Joint Learning of Multi-Scale Essay Representation](https://mlsanity.com/paper/2205.03835/) (2022)
- [Unleashing Large Language Models' Proficiency in Zero-shot Essay Scoring](https://mlsanity.com/paper/2404.04941/) (2024)
- [SMART: Simulated Students Aligned with Item Response Theory for Question Difficulty Prediction](https://mlsanity.com/paper/2507.05129/) (2025)
- [Rationale Behind Essay Scores: Enhancing S-LLM's Multi-Trait Essay Scoring with Rationale Generated by LLMs](https://mlsanity.com/paper/2410.14202/) (2024)
- [Controllable Text Summarization: Unraveling Challenges, Approaches, and Prospects -- A Survey](https://mlsanity.com/paper/2311.09212/) (2023)
- [Can LLMs Reliably Simulate Human Learner Actions? A Simulation Authoring Framework for Open-Ended Learning Environments](https://mlsanity.com/paper/2410.02110/) (2024)
- [Leveraging generative artificial intelligence to simulate student learning behavior](https://mlsanity.com/paper/2310.19206/) (2023)
- [Reinforcement Learning with Token-level Feedback for Controllable Text Generation](https://mlsanity.com/paper/2403.11558/) (2024)
- [MACSum: Controllable Summarization with Mixed Attributes](https://mlsanity.com/paper/2211.05041/) (2022)
- [Autoregressive Multi-trait Essay Scoring via Reinforcement Learning with Scoring-aware Multiple Rewards](https://mlsanity.com/paper/2409.17472/) (2024)
- [Standardize: Aligning Language Models with Expert-Defined Standards for Content Generation](https://mlsanity.com/paper/2402.12593/) (2024)
- [Teach-to-Reason with Scoring: Self-Explainable Rationale-Driven Multi-Trait Essay Scoring](https://mlsanity.com/paper/2502.20748/) (2025)

## Built on by (most cited first, 1 of 1)

- [Error-Supervised Synthetic Learner Writing for Automated Essay Scoring](https://mlsanity.com/paper/2609.23573/) (2026)

## Abstract (arXiv)

Writing proficiency manifests in how students develop content, organize ideas, choose words, and use language. Despite growing interest in LLM-based student simulation, whether LLMs can reproduce such multidimensional variation in extended writing remains largely unexplored. In this work, we explore if language models can realistically simulate student writing, and introduce SWIM, a task that formulates Student Writing sIMulation as proficiency-conditioned essay generation. We evaluate prompting, supervised fine-tuning (SFT), and reinforcement learning (RL) methods for writing simulation using automated essay scoring as a measure of profile alignment. Extensive experiments reveal that prompting provides limited proficiency control, even for strong proprietary LLMs with rubric-grounded strategies. In particular, while models can adjust content-oriented traits, they struggle to reproduce the lexical, grammatical, and organizational variation in different proficiency levels. SFT substantially improves alignment, while RL with the proposed proficiency-alignment reward yields further gains across all writing traits and essay prompts. Our findings suggest that explicit supervision enables substantially stronger profile alignment than prompting alone, while authentic low-proficiency writing remains challenging to reproduce.