用噪声调控生成学生作文的改进版，保持原风格又更优秀。
Gumbel Machine: Counterfactual Student Writing Generation via Gumbel Noise Steering
- 通过控制随机性调节生成文本与原文相似度。
- 在多个评分维度上生成的改写文既符合评分标准又贴近原作。
- 适合教育场景中个性化写作辅导，尤其对自动生成评语有用。
有效的跨学科教学方法是提供高质量作品范例。然而，范例可能与学生当前水平差异过大，难以模仿。理想的示范应是学生原文的反事实改进版本——在保持原有特征基础上的优化。现有基于大语言模型的反事实文本生成方法多为领域专用系统，难以实用化。本文提出 Gumbel Machine，一种灵活、模块化的反事实生成方法，利用大模型的指令遵循能力，并鼓励生成结果与参考文本保持相似。核心是创新的受控解码算法 $β$-Hindsight 控制，通过潜在随机性作为可调相似度控制机制。在多个学生作文数据集上的实验表明，该方法能生成既符合评分标准又与参考文本高度相似的反事实文本。
原文摘要 · Abstract (English)
An effective method of teaching across disciplines is to provide examples of high-quality work. However, an example may be significantly different from a student's current work, making it challenging for them to emulate. An ideal learning demonstration is a counterfactual version of the student work, an improved version that is still similar to their own. 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. 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. Central to our approach is a novel, controlled decoding algorithm, $β$-Hindsight control, which uses latent randomness as a tunable similarity control mechanism during counterfactual generation. Experiments on datasets of student writing, scored on various criteria, demonstrate the effectiveness of our approach at generating counterfactuals both rubric-consistent and similar to a reference.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。