LLMs analyze semiotic relations in mathematical, legal, and everyday arguments

A new study published on arXiv explores the use of large language models (LLMs) to analyze argument structures across different genres. Researchers developed operational definitions for four semiotic relations—syntagmatic, paradigmatic, antithetic, and meronymic—inspired by semiotic research and mapped them to proof methods like inference, analogy, contradiction, and case analysis. The study found significant variations in how these relations are employed, with mathematical proofs utilizing all four, while legal and everyday reasoning predominantly rely on inference. AI

IMPACT This research could lead to more sophisticated AI analysis of complex texts and improved AI reasoning capabilities.

RANK_REASON The cluster contains a research paper published on arXiv detailing a study on LLMs and argument structure. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CL →

• alphaXiv
• arXiv
• CatalyzeX
• DagsHub
• Edirlei Soares De Lima PhD
• Gotit.pub
• Hugging Face
• Influence Flower
• Large Language Models
• ScienceCast

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →