Thinking Through Signs: PEEL as a Semiotic Scaffolding for Epistemically Accountable AI-Enabled Research
Thinking Through Signs: PEEL as a Semiotic Scaffolding for Epistemically Accountable AI-Enabled Research
通过符号进行思考：PEEL——作为认知负责任的 AI 辅助研究的符号学框架
Computer Science > Artificial Intelligence arXiv:2606.04152 (cs) [Submitted on 2 Jun 2026] 计算机科学 > 人工智能 arXiv:2606.04152 (cs) [2026年6月2日提交]
Title: Thinking Through Signs: PEEL as a Semiotic Scaffolding for Epistemically Accountable AI-Enabled Research 标题： 通过符号进行思考：PEEL——作为认知负责任的 AI 辅助研究的符号学框架
Authors: Clarisse de Souza, Gabriel Barbosa, Simone Diniz Junqueira Barbosa, Bárbara Betts, Renato Cerqueira, Juliana Jansen Ferreira 作者： Clarisse de Souza, Gabriel Barbosa, Simone Diniz Junqueira Barbosa, Bárbara Betts, Renato Cerqueira, Juliana Jansen Ferreira
Abstract: Large language models are reshaping research practice while quietly eroding researchers’ epistemic accountability. This commentary introduces PEEL - Protocols for Epistemically Engaged Literacy in AI, a working scaffolding that combines deterministic distant reading via Voyant Tools with LLM interpretation via Claude, grounded in Peircean semiotics and abductive reasoning. 摘要： 大型语言模型正在重塑研究实践，同时也悄然侵蚀着研究人员的认知责任。本文介绍了一种名为 PEEL（AI 认知参与素养协议）的工作框架，它结合了通过 Voyant Tools 进行的确定性远读（distant reading）与通过 Claude 进行的 LLM 解读，并以皮尔士符号学（Peircean semiotics）和溯因推理（abductive reasoning）为基础。
Applied to AI-generated condensations of three source texts, PEEL reveals systematic distortions in quantity, term frequency, and epistemic voice that are invisible without non-AI measurement — and yields three design implications: deterministic instruments must accompany AI tools; fluency is not fidelity; epistemic authority must be designed in, not assumed. 通过对三个源文本的 AI 生成摘要进行应用，PEEL 揭示了在没有非 AI 测量的情况下无法察觉的系统性偏差，这些偏差存在于数量、术语频率和认知语态中。研究得出了三项设计启示：确定性工具必须与 AI 工具配套使用；流畅度不等于忠实度；认知权威必须通过设计来实现，而非理所当然地假设。