Constrained Semantic Decompression in LLMs through Persian Proverb-Conditioned Story Generation

Researchers at arXiv have introduced a constrained semantic decompression task to test whether large language models can transform Persian proverbs into morally faithful narratives. Their study, using the new Proverb Aligned Narrative Dataset (PAND), reveals a persistent "decompression gap" where LLMs achieve surface-level fluency but fail to instantiate the underlying moral and causal structure of proverbs. The findings suggest that explicit reasoning and iterative refinement can partially mitigate these failures, indicating the problem stems from difficulties in translating abstract meaning into narrative form rather than a lack of relevant knowledge.

arXiv:2606.12599v1 Announce Type: new Abstract: 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.