Metraipolis › archive › dc_30976aea115c

SWIM: Student Writing Simulation via Proficiency-Conditioned Generation — arXiv:2609.03215

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.03215
License (as archived)
CC0-1.0
Archived
2026-10-17T01:40:05.757Z
SHA-256 of the archived text
dfa689e1cdb88a10cab2437f5360059b5549117dc785a87df4e984fd79750e69
Stable URL of this page
https://metraipolis.com/documento/dc_30976aea115c

How to cite

SWIM: Student Writing Simulation via Proficiency-Conditioned Generation — arXiv:2609.03215 — arXiv (en), https://arxiv.org/abs/2609.03215 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_30976aea115c (Metraipolis archive dc_30976aea115c, sha256 dfa689e1cdb88a10cab2437f5360059b5549117dc785a87df4e984fd79750e69)
BibTeX
@misc{dc30976aea115c,
  title = {SWIM: Student Writing Simulation via Proficiency-Conditioned Generation — arXiv:2609.03215},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.03215},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_30976aea115c; sha256 dfa689e1cdb88a10cab2437f5360059b5549117dc785a87df4e984fd79750e69},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03215. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-04 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.03215 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T01:11:43.507Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).