# MirrorStories: Reflecting Diversity through Personalized Narrative Generation with Large Language Models

arXiv: https://arxiv.org/abs/2409.13935 · HTML: https://mlsanity.com/paper/2409.13935/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 36 references that are in the map.
- First posted on arXiv 20 Sep 2024.

## Builds on (most cited first, 14 of 14)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks](https://mlsanity.com/paper/2303.15056/) (2023)
- [BERTopic: Neural topic modeling with a class-based TF-IDF procedure](https://mlsanity.com/paper/2203.05794/) (2022)
- [PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traits](https://mlsanity.com/paper/2305.02547/) (2023)
- [InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews](https://mlsanity.com/paper/2310.17976/) (2023)
- [A Confederacy of Models: a Comprehensive Evaluation of LLMs on Creative Writing](https://mlsanity.com/paper/2310.08433/) (2023)
- [StoryGPT-V: Large Language Models as Consistent Story Visualizers](https://mlsanity.com/paper/2312.02252/) (2023)
- [Album Storytelling with Iterative Story-aware Captioning and Large Language Models](https://mlsanity.com/paper/2305.12943/) (2023)
- [UPLex: Fine-Grained Personality Control in Large Language Models via Unsupervised Lexical Modulation](https://mlsanity.com/paper/2310.16582/) (2023)

## Built on by (most cited first, 8 of 8)

- [Biased Tales: Cultural and Topic Bias in Generating Children's Stories](https://mlsanity.com/paper/2509.07908/) (2025)
- [Frankentext: Stitching random text fragments into long-form narratives](https://mlsanity.com/paper/2505.18128/) (2025)
- [Online-PVLM: Advancing Personalized VLMs with Online Concept Learning](https://mlsanity.com/paper/2511.20056/) (2025)
- [GRAVITY: A Framework for Personalized Text Generation via Profile-Grounded Synthetic Preferences](https://mlsanity.com/paper/2510.11952/) (2025)
- [Personality Matters: User Traits Predict LLM Preferences in Multi-Turn Collaborative Tasks](https://mlsanity.com/paper/2508.21628/) (2025)
- [PREFINE: Personalized Story Generation via Simulated User Critics and User-Specific Rubric Generation](https://mlsanity.com/paper/2510.21721/) (2025)
- [NARRA-Gym for Evaluating Interactive Narrative Agents](https://mlsanity.com/paper/2605.08503/) (2026)
- [ReLay: Personalized LLM-Generated Plain-Language Summaries for Better Understanding, but at What Cost?](https://mlsanity.com/paper/2605.00468/) (2026)

## Abstract (arXiv)

This study explores the effectiveness of Large Language Models (LLMs) in creating personalized "mirror stories" that reflect and resonate with individual readers' identities, addressing the significant lack of diversity in literature. We present MirrorStories, a corpus of 1,500 personalized short stories generated by integrating elements such as name, gender, age, ethnicity, reader interest, and story moral. We demonstrate that LLMs can effectively incorporate diverse identity elements into narratives, with human evaluators identifying personalized elements in the stories with high accuracy. Through a comprehensive evaluation involving 26 diverse human judges, we compare the effectiveness of MirrorStories against generic narratives. We find that personalized LLM-generated stories not only outscore generic human-written and LLM-generated ones across all metrics of engagement (with average ratings of 4.22 versus 3.37 on a 5-point scale), but also achieve higher textual diversity while preserving the intended moral. We also provide analyses that include bias assessments and a study on the potential for integrating images into personalized stories.