Thinking Through Signs: PEEL as a Semiotic Scaffolding for Epistemically Accountable AI-Enabled Research
2026-06-02 • Artificial Intelligence
Artificial IntelligenceComputers and Society
AI summaryⓘ
The authors discuss how big language AI models are changing how researchers work but can also reduce how carefully researchers check their knowledge sources. They introduce PEEL, a method combining traditional text analysis tools with AI interpretation, based on ideas from semiotics and reasoning techniques. Using PEEL on AI summaries of texts, the authors found hidden biases and changes that AI alone might miss. They suggest combining fixed analysis tools with AI, recognizing that sounding natural doesn’t mean being accurate, and designing clear ways to show which information is trustworthy.
Large Language ModelsEpistemic AccountabilityVoyant ToolsClaude (LLM)Peircean SemioticsAbductive ReasoningDeterministic Distant ReadingEpistemic VoiceAI-generated SummarizationDesign Implications
Authors
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. 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.