LLMs Got Rhythm? Hybrid Phonological Filtering for Greek Poetry Rhyme Detection and Generation

TL;DR

This paper introduces a hybrid system combining Large Language Models with phonological algorithms to improve rhyme detection and generation in Greek poetry, addressing limitations of LLMs in phonologically-grounded tasks.

Contribution

It presents a novel hybrid approach with a taxonomy of Greek rhyme types and a phonological verification pipeline, significantly enhancing rhyme generation accuracy in Greek poetry.

Findings

Native-like models perform with 40% accuracy in rhyme identification.

Reasoning-heavy models reach 54% accuracy with Chain-of-Thought prompting.

Hybrid verification boosts rhyme generation success to 73.1%.

Abstract

Large Language Models (LLMs), despite their remarkable capabilities across NLP tasks, struggle with phonologically-grounded phenomena like rhyme detection and generation. This is even more evident in lower-resource languages such as Modern Greek. In this paper, we present a hybrid system that combines LLMs with deterministic phonological algorithms to achieve accurate rhyme identification/analysis and generation. Our approach implements a comprehensive taxonomy of Greek rhyme types, including Pure, Rich, Imperfect, Mosaic, and Identical Pre-rhyme Vowel (IDV) patterns, and employs an agentic generation pipeline with phonological verification. We evaluate multiple prompting strategies (zero-shot, few-shot, Chain-of-Thought, and RAG-augmented) across several LLMs including Claude 3.7 and 4.5, GPT-4o, Gemini 2.0 and open-weight models like Llama 3.1 8B and 70B and Mistral Large. Results reveal a significant "Reasoning Gap": while native-like models (Claude 3.7) perform intuitively (40\% accuracy in identification), reasoning-heavy models (Claude 4.5) achieve state-of-the-art performance (54\%) only when prompted with Chain-of-Thought. Most critically, pure LLM generation fails catastrophically (under 4\% valid poems), while our hybrid verification loop restores performance to 73.1\%. We release our system and a corpus of 40,000+ rhymes, derived from the Anemoskala and Interwar Poetry corpora, to support future research.