超越通过与否：图灵测试的信息加工解释
Beyond pass or fail: an information-processing account of the Turing Test
arXiv:2610.32868v1 公告类型：新摘要：当人类审问者无法区分机器生成的回答与人类的回答时，图灵测试即被通过。然而，行为上的不可区分性可能反映两种根本不同的失败：编码失败，即机器与人类的输出分布重叠得如此紧密，以至于来源信息实际上不存在；或读取失败，即来源信息存在，但审问者未能将其提取出来。为了区分这两种可能性，我们反转了图灵测试，将人类与 AI 系统置于对称的审问者角色中。使用一个定量的信息处理框架，我们分离了编码（文本中所包含的信息）、读取（审问者对该信息的提取）以及元读取（审问者对其自身判断所依据特征的显式访问）。在涉及超过 3800 名人类审问者和两代 GPT 模型（GPT-4 与 GPT-5）的两个系列实验中，我们发现了跨加工水平和审问者类型的显著分离。随着 AI 生成的回答从 GPT-4 到 GPT-5 变得更加像人类，来源信息对於人类审问者而言变得更难提取。相比之下，GPT-5 审问者比 GPT-4 审问者更准确地读取来源区分信息。然而，这一改进伴随着一个特定的局限：GPT-5 的解释仅部分地与实际预测其判断的特征权重相一致。人类审问者则表现出互补的模式，读取一致性适中，但元读取一致性相对更高。总之，这些发现表明人类与 GPT 审问者在读取与元读取之间存在双重分离。
把图灵测试拆成编码、读取与元读取三个层次，并用人类与GPT互为审问者的对称设计分离两种失败。
arXiv:2610.32868v1 Announce Type: new Abstract: The Turing Test is passed when a human interrogator cannot distinguish machine-generated responses from human ones. Yet behavioral indistinguishability can reflect two fundamentally different failures: a failure of encoding, in which machine and human output distributions overlap so closely that source information is effectively absent; or a failure of readout, in which source information is present but the interrogator fails to extract it. To dissociate these possibilities, we inverted the Turing Test, placing humans and AI systems in symmetrical interrogator roles. Using a quantitative information-processing framework, we separated encoding, the information contained in the text; readout, the extraction of that information by an interrogator; and meta-readout, the interrogator's explicit access to the features guiding its own judgments. Across two series of experiments involving more than 3800 human interrogators and two generations of GPT models (GPT-4 and GPT-5), we found a striking dissociation across processing levels and interrogator types. As AI-generated responses became more human-like from GPT-4 to GPT-5, source information became more difficult for human interrogators to extract. GPT-5 interrogators, by contrast, read out source-discriminating information more accurately than GPT-4 interrogators. This improvement, however, came with a specific limitation: GPT-5 explanations only partially aligned with the feature weightings that actually predicted their judgments. Human interrogators showed the complementary pattern, with modest readout alignment but comparatively higher meta-readout alignment. Together, these findings suggest a double dissociation between readout and meta-readout across human and GPT interrogators.
中文翻译还没有生成，先显示原文。
来源：arXiv · Human-Computer Interaction · arxiv.org