Structuralist Approach to AI Literary Criticism: Leveraging Greimas Semiotic Square for Large Language Models
This provides an AI tool for literary research and education, addressing a domain-specific problem with incremental improvements in structured analysis.
The paper tackles LLMs' difficulty in providing professional literary criticism for complex narratives by proposing GLASS, a framework based on the Greimas Semiotic Square, which shows high performance compared to expert criticism and produces original analyses for 39 classic works.
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.