arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2605.06294cs.CLcs.AIcs.LG
收藏

对数似然、辛普森悖论与机器生成文本的检测

Log-Likelihood, Simpson's Paradox, and the Detection of Machine-Generated Text

Department of Mathematics(数学系);University of Manchester(曼彻斯特大学);Risk and Security AI Lab(风险与安全AI实验室);Visa Inc.(Visa公司)

Tom Kempton, Viktor Drobnyi, Maeve Madigan, Stuart Burrell

AI总结:

本文通过分析对数似然信号在隐藏空间中的非均匀性,提出基于贝叶斯决策理论的局部校准方法,改进文本检测性能,揭示现有检测器的不足并提供可扩展的解决方案。

摘要:

可靠区分人类文本与大语言模型生成文本的能力对社会具有深远意义。主流方法基于似然假设:机器生成文本对检测器语言模型更可能。然而,我们证明在检测器模型的隐藏空间中,区分人类和机器文本的token级信号非均匀分布,简单平均基于似然的token得分会导致辛普森悖论:强局部信号被不当聚合破坏。为此,我们引入基于贝叶斯决策理论的学得局部校准步骤。而非简单聚合原始token得分,我们首先学习轻量级的得分分布预测器,条件于隐藏空间位置,并聚合校准后的对数似然比。这一干预显著且一致地提高了所有基线检测器和数据集的检测性能。例如,我们改进的Fast-DetectGPT在GPT-5.4文本上将AUROC从0.63提升到0.85,我们引入的局部校准DMAP检测器在各方面达到最佳性能。然而,我们的核心贡献不是新的检测器,而是对现有检测器性能不足的根本原因的精确诊断以及一种与任何token平均管道兼容的原理性、模块化解决方案。这将为社区提供基础,自然路径包括更丰富的分布模型、改进的校准策略以及通过完整贝叶斯最优决策规则进行的隐藏空间几何信号的原理性融合。

英文摘要:

The ability to reliably distinguish human-written text from that generated by large language models is of profound societal importance. The dominant approach to this problem exploits the likelihood hypothesis: that machine-generated text should appear more probable to a detector language model than human-written text. However, we demonstrate that the token-level signal distinguishing human and machine text is non-uniform across the hidden space of the detector model, and naively averaging likelihood-based token scores across regions with fundamentally different statistical structure, as most detectors do, causes a form of Simpson's paradox: a strong local signal is destroyed by inappropriate aggregation. To correct for this, we introduce a learned local calibration step grounded in Bayesian decision theory. Rather than aggregating raw token scores, we first learn lightweight predictors of the score distributions conditioned on position in hidden space, and aggregate calibrated log-likelihood ratios instead. This single intervention dramatically and consistently improves detection performance across all baseline detectors and all datasets we consider. For example, our calibrated variant of Fast-DetectGPT improves AUROC from $0.63$ to $0.85$ on GPT-5.4 text, and a locally-calibrated DMAP detector we introduce achieves state-of-the-art performance across the board. That said, our central contribution is not a new detector, but a precise diagnosis of a significant cause of under-performance of existing detectors and a principled, modular remedy compatible with any token-averaging pipeline. This will serve as a foundation for the community to build upon, with natural avenues including richer distributional models, improved calibration strategies, and principled ensembling with hidden-space geometry signals via the full Bayes-optimal decision rule.

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。

↑