SWIM: Student Writing Simulation via Proficiency-Conditioned Generation

• URL: http://arxiv.org/abs/2609.03215v1
• Date: Wed, 02 Sep 2026 23:10:51 GMT
• Title: SWIM: Student Writing Simulation via Proficiency-Conditioned Generation
• Abstract summary: This work explores if language models can realistically simulate student writing, and introduce SWIM.<n>We evaluate prompting, supervised fine-tuning, and reinforcement learning methods for writing simulation using automated essay scoring as a measure of profile alignment.<n>Our findings suggest that explicit supervision enables substantially stronger profile alignment than prompting alone, while authentic low-proficiency writing remains challenging to reproduce.
• Score: 54.69949380133243
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• CLIN: an Objective Framework for Evaluating Creativity in Short Persian Literary Text [15.007368492314308]
  evaluating creativity in large language model (LLM) outputs remains challenging because creativity is multidimensional and human-centered.<n>We examine how reliably LLMs evaluate short literary text in Persian, a low-resource language.<n>We find that alignment is stronger for structured TTCT-derived properties such as Originality, Fluency, and Elaboration, but weaker for more subjective dimensions, particularly Emotion and Attractiveness.<n>Motivated by this dimension-dependent behavior, we investigate whether structured creativity dimensions can instead be approximated using simple, interpretable proxy metrics.
  arXiv  Detail & Related papers  (2026-08-31T13:22:20Z)
• Revising Context, Shifting Simulated Stance: Auditing LLM-Based Stance Simulation in Online Discussions [62.99524765341952]
  Large language models are increasingly used to simulate social media users.<n>We study counterfactual context revision as a framework for auditing LLM-based stance simulation.<n>Results reveal effective and robust stance transitions in both text-only and multimodal strategies.
  arXiv  Detail & Related papers  (2026-06-04T17:41:54Z)
• The Crutch or the Ceiling? How Different Generations of LLMs Shape EFL Student Writings [0.26097841018267615]
  This study explores the extent and limitations of Large Language Models (LLMs) in assisting secondary-level English as a Foreign Language (EFL) students with their writing tasks.<n>Our results indicate that advanced LLMs boost assessment scores and lexical diversity for lower-proficiency learners.<n>To transform AI-assisted practice into genuine learning, pedagogy must shift from focusing on output quality to verifying the learning process.
  arXiv  Detail & Related papers  (2026-04-16T18:19:46Z)
• Intention-Adaptive LLM Fine-Tuning for Text Revision Generation [0.70303436819479]
  Large Language Models (LLMs) have achieved impressive capabilities in context-based text generation tasks.<n>We propose Intention-Tuning, an intention-adaptive layer-wise LLM fine-tuning framework.<n>We show that Intention-Tuning is effective and efficient on small revision corpora.
  arXiv  Detail & Related papers  (2026-01-31T03:01:09Z)
• LangSuitE: Planning, Controlling and Interacting with Large Language Models in Embodied Text Environments [70.91258869156353]
  We introduce LangSuitE, a versatile and simulation-free testbed featuring 6 representative embodied tasks in textual embodied worlds. Compared with previous LLM-based testbeds, LangSuitE offers adaptability to diverse environments without multiple simulation engines. We devise a novel chain-of-thought (CoT) schema, EmMem, which summarizes embodied states w.r.t. history information.
  arXiv  Detail & Related papers  (2024-06-24T03:36:29Z)
• LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models [56.25156596019168]
  This paper introduces the LMRL-Gym benchmark for evaluating multi-turn RL for large language models (LLMs) Our benchmark consists of 8 different language tasks, which require multiple rounds of language interaction and cover a range of tasks in open-ended dialogue and text games.
  arXiv  Detail & Related papers  (2023-11-30T03:59:31Z)
• CLOMO: Counterfactual Logical Modification with Large Language Models [109.60793869938534]
  We introduce a novel task, Counterfactual Logical Modification (CLOMO), and a high-quality human-annotated benchmark. In this task, LLMs must adeptly alter a given argumentative text to uphold a predetermined logical relationship. We propose an innovative evaluation metric, the Self-Evaluation Score (SES), to directly evaluate the natural language output of LLMs.
  arXiv  Detail & Related papers  (2023-11-29T08:29:54Z)
• AlignedCoT: Prompting Large Language Models via Native-Speaking Demonstrations [52.43593893122206]
  Alignedcot is an in-context learning technique for invoking Large Language Models. It achieves consistent and correct step-wise prompts in zero-shot scenarios. We conduct experiments on mathematical reasoning and commonsense reasoning.
  arXiv  Detail & Related papers  (2023-11-22T17:24:21Z)
• AI Text-to-Behavior: A Study In Steerability [0.0]
  The research explores the steerability of Large Language Models (LLMs) We quantitatively gauged the model's responsiveness to tailored prompts using a behavioral psychology framework called OCEAN. Our findings underscore GPT's versatility and ability to discern and adapt to nuanced instructions.
  arXiv  Detail & Related papers  (2023-08-07T18:14:24Z)
• RLPrompt: Optimizing Discrete Text Prompts With Reinforcement Learning [84.75064077323098]
  This paper proposes RLPrompt, an efficient discrete prompt optimization approach with reinforcement learning (RL) RLPrompt is flexibly applicable to different types of LMs, such as masked gibberish (e.g., grammaBERT) and left-to-right models (e.g., GPTs) Experiments on few-shot classification and unsupervised text style transfer show superior performance over a wide range of existing finetuning or prompting methods.
  arXiv  Detail & Related papers  (2022-05-25T07:50:31Z)

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.