Constrained Semantic Decompression in LLMs through Persian Proverb-Conditioned Story Generation
For researchers in narrative generation and cultural AI, this work identifies and characterizes a persistent failure mode in LLMs when translating abstract cultural knowledge into concrete narratives.
The paper introduces a constrained semantic decompression task using Persian proverbs to generate stories, revealing a decompression gap where LLMs produce fluent narratives but fail to faithfully convey the underlying moral structure. Explicit reasoning and iterative refinement partially mitigate this gap.
Transforming a dense, abstract proverb into an engaging and morally faithful narrative requires deep cultural understanding and robust semantic grounding. We frame this problem as a \emph{constrained semantic decompression} task and study proverb-conditioned story generation as a testbed for abstraction-to-realization in large language models (LLMs). Focusing on Persian, we introduce the Proverb Aligned Narrative Dataset (PAND), pairing proverbs with human-written stories and explicit meanings. By a hybrid evaluation framework that combines human-calibrated LLM-as-a-Judge with structural metrics, we analyze model behavior across multiple prompting regimes. Our findings reveal a persistent \emph{decompression gap}: current LLMs often achieve strong surface-level fluency while failing to faithfully instantiate the underlying moral and causal structure encoded in proverbs. We further show that explicit reasoning and iterative refinement can partially mitigate these failures, suggesting that many decompression errors arise from difficulties in translating abstract meaning into narrative form rather than a complete lack of relevant knowledge. Our proposed task naturally extends to other forms of compressed cultural knowledge.