arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2601.01966cs.LGcs.AI
收藏

细化溯源推断:从模型行为检测LLM细化训练提示

Refinement Provenance Inference: Detecting LLM-Refined Training Prompts from Model Behavior

National University of Singapore(新加坡国立大学)

Bo Yin, Qi Li, Runpeng Yu, Xinchao Wang

AI总结:

本文提出RePro框架,通过教师强制的似然特征与logit排名信号融合,实现对LLM细化训练提示的溯源推断,具有跨模型和训练设置的泛化能力。

摘要:

指令微调越来越多地依赖于基于LLM的提示细化,其中训练语料库中的提示被外部细化器选择性地重写以提高清晰度和指令对齐。这促使了一个实例级审计问题:对于一个微调后的模型和一个训练提示-响应对,我们能否推断出该模型是否在混合语料库中被训练于原始提示或其LLM细化版本?这对于数据集治理和争议解决非常重要,当训练数据受到质疑时。然而,实践中并不简单:细化和原始实例在训练语料库中交错出现,混合比例未知且依赖于来源,这使得开发能够跨模型和训练设置通用的溯源方法更加困难。在本文中,我们将这一审计任务正式化为细化溯源推断(RPI),并证明提示细化会导致教师强制令牌分布的稳定、可检测的转变,即使在语义差异不明显的情况下也是如此。基于这一现象,我们提出了RePro,一种基于logit的溯源框架,该框架融合了教师强制的似然特征与logit排名信号。在训练过程中,RePro通过影子微调学习一个可转移的表示,并使用一个轻量级的线性头来推断未见过的受害者上的溯源,而无需访问训练数据。经验上,RePro在各种情况下都取得了强劲的性能,并且能够跨细化器良好转移,表明它利用的是与细化器无关的分布转变,而不是重写式痕迹。

英文摘要:

Instruction tuning increasingly relies on LLM-based prompt refinement, where prompts in the training corpus are selectively rewritten by an external refiner to improve clarity and instruction alignment. This motivates an instance-level audit problem: for a fine-tuned model and a training prompt-response pair, can we infer whether the model was trained on the original prompt or its LLM-refined version within a mixed corpus? This matters for dataset governance and dispute resolution when training data are contested. However, it is non-trivial in practice: refined and raw instances are interleaved in the training corpus with unknown, source-dependent mixture ratios, making it harder to develop provenance methods that generalize across models and training setups. In this paper, we formalize this audit task as Refinement Provenance Inference (RPI) and show that prompt refinement yields stable, detectable shifts in teacher-forced token distributions, even when semantic differences are not obvious. Building on this phenomenon, we propose RePro, a logit-based provenance framework that fuses teacher-forced likelihood features with logit-ranking signals. During training, RePro learns a transferable representation via shadow fine-tuning, and uses a lightweight linear head to infer provenance on unseen victims without training-data access. Empirically, RePro consistently attains strong performance and transfers well across refiners, suggesting that it exploits refiner-agnostic distribution shifts rather than rewrite-style artifacts.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑