AI 中文总结
研究自然语言中分布漂移检测问题，提出基于有向k近邻图的非对称双样本测试ASK-NN，其计算高效易实现，在合成基准、人工文本及LLM幻觉检测方面与核和图基线相比具有竞争力。
AI 中文摘要
大语言模型（LLM）生成输出中的幻觉和人工文本常表现为提示与响应隐藏状态分布之间的分布偏差。由于提示或检索到的上下文通常作为参考样本，响应作为查询样本，且长度差异较大，这些不对称性促使使用对两个样本区别对待的变化测试统计量。我们考虑基于有向k近邻图的非对称双样本测试ASK-NN。我们的统计量计算在合并样本中最近邻也是参考点的参考点数量。在排列零假设下，它具有精确的有限样本条件均值和方差；我们还在固定备择假设下建立了渐近正态性和一致性。ASK-NN计算高效且易于实现。实证上，它在合成基准、人工文本检测和基于令牌级隐藏状态的LLM幻觉检测方面与基于核和图的基线具有竞争力。
英文摘要
Hallucinations and artificial text in LLM-generated outputs often appear as distributional deviations between prompt and response hidden-state distributions. Since prompts or retrieved contexts typically serve as reference samples and responses as query samples, with major differences in length, these asymmetries motivate the use of change test statistics that treat the two samples differently. We consider an asymmetric two-sample test ASK-NN based on the directed k-nearest-neighbor graph. Our statistic counts reference points whose nearest neighbor in the pooled sample is also a reference point. Under the permutation null, it admits an exact finite-sample conditional mean and variance; we further establish asymptotic normality and consistency under fixed alternatives. ASK-NN is computationally effective and easy to implement. Empirically, it is competitive with kernel and graph-based baselines on synthetic benchmarks, artificial-text detection, and LLM hallucination detection from token-level hidden states.
Comments9 pages, 4 figures
