Structuralist Approach to AI Literary Criticism: Leveraging Greimas Semiotic Square for Large Language Models

2025-06-26

AI Summary

Large language models (LLMs) exhibit limited capability in professional literary criticism—particularly for intellectually dense and narratively complex canonical texts. Method: We propose GLASS, a novel literary criticism framework that pioneers structured guidance via the Greimasian semiotic square, integrating prompt engineering, structured chain-of-reasoning design, and LLM fine-tuning. We construct GSS, the first Greimas-structured annotation dataset covering 48 canonical works, and introduce an LLM-as-a-judge metric for quantitative evaluation. Contribution/Results: Experiments demonstrate that GLASS significantly outperforms general-purpose LLMs in critical depth and interpretive rigor across multiple canonical texts, achieving expert-level quality. To date, it has generated original, high-fidelity critical analyses for 39 works—establishing the first scalable, AI-driven paradigm for deep literary scholarship and filling a critical gap in computational humanities research.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Sentiment Analysis, Stylistic Analysis, and Argument Mining
• Cognitive Modeling & Cognitive Systems: Computational Creativity

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Large language models for search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Large Language Models (LLMs) excel in understanding and generating text but struggle with providing professional literary criticism for works with profound thoughts and complex narratives. This paper proposes GLASS (Greimas Literary Analysis via Semiotic Square), a structured analytical framework based on Greimas Semiotic Square (GSS), to enhance LLMs' ability to conduct in-depth literary analysis. GLASS facilitates the rapid dissection of narrative structures and deep meanings in narrative works. We propose the first dataset for GSS-based literary criticism, featuring detailed analyses of 48 works. Then we propose quantitative metrics for GSS-based literary criticism using the LLM-as-a-judge paradigm. Our framework's results, compared with expert criticism across multiple works and LLMs, show high performance. Finally, we applied GLASS to 39 classic works, producing original and high-quality analyses that address existing research gaps. This research provides an AI-based tool for literary research and education, offering insights into the cognitive mechanisms underlying literary engagement.

Problem

• Enhancing LLMs' ability for professional literary criticism
• Providing structured analysis of narrative works
• Addressing gaps in AI-based literary research tools

Innovation

• GLASS framework enhances LLM literary analysis
• First dataset for GSS-based literary criticism
• Quantitative metrics using LLM-as-a-judge paradigm