LA-CPD：面向人机合著篇章归属分割的局部证据感知变点检测

中文摘要 AI 辅助

随着大语言模型（LLM）生成的文本日益接近人类写作风格，在涉及版权侵权、欺诈及其他有害使用AI生成内容的案件中，准确定位人机合著文档中由LLM撰写的片段，对于归属认定和问责至关重要。句子级检测器可提供局部归属证据，但内容差异可能导致同一来源的句子之间出现分数波动，从而产生虚假边界。当归属转换的数量和位置均未知时，恢复连贯的文档分割仍具挑战性。我们提出局部证据感知变点检测（LA-CPD），这是一种结构化方法，可将噪声较大的句子级分数序列转化为连贯的归属片段。给定冻结的局部检测器输出的分数，LA-CPD将长度加权的片段内残差与窗口化双均值对比相结合，以捕捉候选切分点周围的片段一致性与持续性变化。动态规划针对每个候选片段数量优化切分位置，而类AIC准则选择最终分割，从而输出句子标签、归属边界及最大LLM撰写片段。在留出的人机合著测试集上，LA-CPD优于WCP+AIC，将句子级准确率从0.747提升至0.796，同时改善了边界定位与LLM片段划分。

英文摘要

As LLM-generated text becomes increasingly human-like, accurately localizing LLM-authored spans in human-LLM co-authored documents is important for attribution and accountability in cases involving copyright infringement, fraud, and other harmful uses of AI-generated content. Sentence-level detectors provide local authorship evidence, but content variation can cause score fluctuations even among sentences from the same source, creating spurious boundaries. Recovering a coherent document partition therefore remains challenging when both the number and locations of authorship transitions are unknown. We propose Local-Evidence-Aware Change-Point Detection (LA-CPD), a structured method that transforms noisy sentence-level score sequences into coherent authorship segments. Given scores from a frozen local detector, LA-CPD combines a length-weighted within-segment residual with a windowed two-mean contrast to capture segment consistency and sustained changes around candidate cut points. Dynamic programming optimizes cut locations for each candidate count, while an AIC-style criterion selects the final partition, yielding sentence labels, authorship boundaries, and maximal LLM-authored spans. On a held-out human-LLM co-authored test set, LA-CPD outperforms WCP+AIC, increasing sentence-level accuracy from 0.747 to 0.796 while improving boundary localization and LLM-span delineation.

发表机构

• Guilin University of Electronic Technology（桂林电子科技大学）
• Jilin University（吉林大学）
• Nanjing University of Science and Technology（南京理工大学）

机构由 AI 辅助整理，请以论文原文为准。