检测小模型训练数据是否包含大模型推理的题目，防止评估结果虚高。
Detecting Distillation Data from Reasoning Models
- 通过分析模型生成答案时的词概率模式，判断问题是否曾出现在训练数据中。
- 在多个数据集上使检测准确率提升最高达31%，显著优于现有方法。
- 适用于模型评估、数据安全和可信机器学习场景，尤其适合关注模型泄露的研究者。
推理蒸馏已成为将大型推理模型的能力迁移至小型语言模型的主流范式。然而，该过程存在数据污染风险：基准测试数据可能意外地被包含在蒸馏数据中，从而人为抬高模型性能指标。本文首次正式定义了蒸馏数据检测任务，即判断给定问题是否出现在模型的蒸馏数据中。该任务的独特挑战在于蒸馏数据部分不可见。为此，我们提出令牌概率偏差（TPD）检测方法，利用模型生成输出令牌的概率模式而非输入令牌进行判断。其核心思想是：已见过的问题通常会引发模型生成更接近确定性的输出令牌，而未见过的问题则不然。因此，TPD分数通过量化生成令牌与高置信度参考概率之间的偏离程度，使得已见问题的得分远低于未见问题，从而实现强检测性能。大量实验表明，该方法在蒸馏数据集上将检测AUC最高提升31%。
原文摘要 · Abstract (English)
Reasoning distillation has emerged as a prevailing paradigm for transferring reasoning capabilities from large reasoning models to small language models. Yet, reasoning distillation risks data contamination: benchmark data may inadvertently be included in the distillation data, thereby inflating model performance metrics. In this work, we formally define the distillation data detection task, which determines whether a given question is included in the model's distillation data. The unique challenge of this task lies in the partial availability of distillation data. To address this, we propose Token Probability Deviation (TPD), a detection method that leverages the probability patterns of output tokens generated by the model instead of input tokens. Our method is motivated by the observation that seen questions tend to elicit more near-deterministic tokens generated by the models than unseen ones. Our TPD score is thus designed to quantify the token-level deviation of generated tokens from a high-confidence reference probability. Consequently, seen questions can yield substantially lower TPD scores than unseen ones, enabling strong detection performance. Extensive experiments demonstrate the effectiveness of our approach, improving detection AUC by up to 31% on distillation datasets.
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。