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

arXiv: https://arxiv.org/abs/2606.12599 · HTML: https://mlsanity.com/paper/2606.12599/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 64 references that are in the map.
- First posted on arXiv 10 Jun 2026.

## Builds on (most cited first, 27 of 27)

- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge](https://mlsanity.com/paper/2411.16594/) (2024)
- [Plan-And-Write: Towards Better Automatic Storytelling](https://mlsanity.com/paper/1811.05701/) (2018)
- [Re3: Generating Longer Stories With Recursive Reprompting and Revision](https://mlsanity.com/paper/2210.06774/) (2022)
- [Does Writing with Language Models Reduce Content Diversity?](https://mlsanity.com/paper/2309.05196/) (2023)
- [Strategies for Structuring Story Generation](https://mlsanity.com/paper/1902.01109/) (2019)
- [A Confederacy of Models: a Comprehensive Evaluation of LLMs on Creative Writing](https://mlsanity.com/paper/2310.08433/) (2023)
- [Content Planning for Neural Story Generation with Aristotelian Rescoring](https://mlsanity.com/paper/2009.09870/) (2020)
- [Are Large Language Models Capable of Generating Human-Level Narratives?](https://mlsanity.com/paper/2407.13248/) (2024)
- [Of Human Criteria and Automatic Metrics: A Benchmark of the Evaluation of Story Generation](https://mlsanity.com/paper/2208.11646/) (2022)
- [AI Suggestions Homogenize Writing Toward Western Styles and Diminish Cultural Nuances](https://mlsanity.com/paper/2409.11360/) (2024)
- [Agents' Room: Narrative Generation through Multi-step Collaboration](https://mlsanity.com/paper/2410.02603/) (2024)
- [AI as Humanity's Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Text](https://mlsanity.com/paper/2410.04265/) (2024)
- [Generating Long-form Story Using Dynamic Hierarchical Outlining with Memory-Enhancement](https://mlsanity.com/paper/2412.13575/) (2024)
- [Pron vs Prompt: Can Large Language Models already Challenge a World-Class Fiction Author at Creative Text Writing?](https://mlsanity.com/paper/2407.01119/) (2024)
- [CS4: Measuring the Creativity of Large Language Models Automatically by Controlling the Number of Story-Writing Constraints](https://mlsanity.com/paper/2410.04197/) (2024)
- [Collective Critics for Creative Story Generation](https://mlsanity.com/paper/2410.02428/) (2024)
- [Jawaher: A Multidialectal Dataset of Arabic Proverbs for LLM Benchmarking](https://mlsanity.com/paper/2503.00231/) (2025)
- [Small Language Models can Outperform Humans in Short Creative Writing: A Study Comparing SLMs with Humans and LLMs](https://mlsanity.com/paper/2409.11547/) (2024)
- [A Corpus for Understanding and Generating Moral Stories](https://mlsanity.com/paper/2204.09438/) (2022)
- [Biased Tales: Cultural and Topic Bias in Generating Children's Stories](https://mlsanity.com/paper/2509.07908/) (2025)
- [ePiC: Employing Proverbs in Context as a Benchmark for Abstract Language Understanding](https://mlsanity.com/paper/2109.06838/) (2021)
- [Benchmarking Large Language Models for Persian: A Preliminary Study Focusing on ChatGPT](https://mlsanity.com/paper/2404.02403/) (2024)
- [MORABLES: A Benchmark for Assessing Abstract Moral Reasoning in LLMs with Fables](https://mlsanity.com/paper/2509.12371/) (2025)
- [Towards Understanding Self-play for LLM Reasoning](https://mlsanity.com/paper/2510.27072/) (2025)
- [Evaluating the Evaluators: Are readability metrics good measures of readability?](https://mlsanity.com/paper/2508.19221/) (2025)
- [Plug-and-Play Dramaturge: A Divide-and-Conquer Approach for Iterative Narrative Script Refinement via Collaborative LLM Agents](https://mlsanity.com/paper/2510.05188/) (2025)

## Abstract (arXiv)

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 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 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.