保护推理过程不被窃取，同时保留有用信息。
Information-Preserving Reformulation of Reasoning Traces for Antidistillation
- 通过去除自言自语和重排子结论，重构推理链。
- 使32B模型在AIME 2024上性能下降13.5%。
- 小辅助模型实现，计算开销极低，适合部署。
大型语言模型的推理链越长，复杂任务表现越好。然而，详细推理过程易被未经授权的模型蒸馏复制，威胁知识产权。为解决这一矛盾，我们提出PART——一种保持信息完整性的推理链反蒸馏重构方法。受人类与模型对推理理解差异启发，设计两步重构：移除自言自语行为，重排子结论顺序。仅需一个小型辅助模型训练即可完成，计算开销极小。大量实验表明，该方法在不同规模与类型的学生模型上均能有效干扰蒸馏。例如，在AIME 2024上，32B模型使用重构推理链训练后，准确率从54.17降至46.88，降幅达13.5%。
原文摘要 · Abstract (English)
Recent advances in Large Language Models (LLMs) show that extending the length of reasoning chains significantly improves performance on complex tasks. While revealing these reasoning traces helps users better follow, verify, and learn from the model's problem-solving process, it also makes them highly vulnerable to unauthorized distillation. To mitigate this risk, proprietary model providers often adopt aggressive protection strategies, such as replacing detailed reasoning with brief summaries, which deprive users of valuable intermediate information. To address this trade-off, we propose PART, an information-preserving antidistillation reformulation of reasoning traces. Motivated by the difference between how humans understand reasoning traces and how LLMs exploit them for supervised fine-tuning, we design a simple but effective two-step reformulation: removing self-talk behaviors and reordering sub-conclusions. A small auxiliary model is trained to perform this reformulation, incurring minimal computational overhead. Extensive experiments demonstrate that PART consistently disrupts distillation across student models of different sizes and types on various reasoning benchmarks. For instance, when training on reformulated traces, even the performance of a large 32B student model decreases from 54.17 to 46.88 on AIME 2024, corresponding to a 13.5% degradation.
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。