Constrained Semantic Decompression in LLMs through Persian Proverb-Conditioned Story Generation
Quick Answer
This study introduces the Proverb Aligned Narrative Dataset (PAND) for proverb-conditioned story generation in Persian, revealing a significant 'decompression gap' in LLMs.
Quick Take
Current models excel in fluency but struggle to accurately convey the moral and causal structures of proverbs, indicating a need for improved reasoning and refinement techniques.
Key Points
- PAND pairs Persian proverbs with human-written stories and meanings.
- show strong fluency but fail to capture underlying moral structures.
- Explicit reasoning can partially reduce decompression errors in narratives.
- The task can extend to other forms of compressed cultural knowledge.
Paper Resources
Article Content
From source RSS / original summaryarXiv: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 (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.
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CL
See more →TriAgent: Divergence-Aware Committees for Cost-Efficient Financial Sentiment Analysis
TriAgent introduces a cost-efficient multi-agent system for financial sentiment analysis, combining VADER, FinBERT, and Qwen2.5. It achieves an F1 score of ~0.87 with significant savings of $9.3M/year at a 10M-user scale compared to GPT-4o-mini, while also detecting hallucinations with an AUC of 0.90.