# SCORE: Story Coherence and Retrieval Enhancement for AI Narratives

arXiv: https://arxiv.org/abs/2503.23512 · HTML: https://mlsanity.com/paper/2503.23512/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 51 references that are in the map.
- First posted on arXiv 30 Mar 2025.

## Builds on (most cited first, 26 of 26)

- [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)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [LaMDA: Language Models for Dialog Applications](https://mlsanity.com/paper/2201.08239/) (2022)
- [A Survey on the Memory Mechanism of Large Language Model based Agents](https://mlsanity.com/paper/2404.13501/) (2024)
- [The Faiss library](https://mlsanity.com/paper/2401.08281/) (2024)
- [All That's 'Human' Is Not Gold: Evaluating Human Evaluation of Generated Text](https://mlsanity.com/paper/2107.00061/) (2021)
- [Evaluation of Text Generation: A Survey](https://mlsanity.com/paper/2006.14799/) (2020)
- [TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methods](https://mlsanity.com/paper/2403.20150/) (2024)
- [DUET: Dual Clustering Enhanced Multivariate Time Series Forecasting](https://mlsanity.com/paper/2412.10859/) (2024)
- [Of Human Criteria and Automatic Metrics: A Benchmark of the Evaluation of Story Generation](https://mlsanity.com/paper/2208.11646/) (2022)
- [SEED-Story: Multimodal Long Story Generation with Large Language Model](https://mlsanity.com/paper/2407.08683/) (2024)
- [Self-evolving Agents with reflective and memory-augmented abilities](https://mlsanity.com/paper/2409.00872/) (2024)
- [Towards Visual-Prompt Temporal Answering Grounding in Medical Instructional Video](https://mlsanity.com/paper/2203.06667/) (2022)
- [Do Language Models Enjoy Their Own Stories? Prompting Large Language Models for Automatic Story Evaluation](https://mlsanity.com/paper/2405.13769/) (2024)
- [More but Correct: Generating Diversified and Entity-revised Medical Response](https://mlsanity.com/paper/2108.01266/) (2021)
- [EasyTime: Time Series Forecasting Made Easy](https://mlsanity.com/paper/2412.17603/) (2024)
- [What Makes a Good Story and How Can We Measure It? A Comprehensive Survey of Story Evaluation](https://mlsanity.com/paper/2408.14622/) (2024)
- [RoleCraft-GLM: Advancing Personalized Role-Playing in Large Language Models](https://mlsanity.com/paper/2401.09432/) (2023)
- [Guiding and Diversifying LLM-Based Story Generation via Answer Set Programming](https://mlsanity.com/paper/2406.00554/) (2024)
- [Bilateral Personalized Dialogue Generation with Contrastive Learning](https://mlsanity.com/paper/2106.07857/) (2021)
- [FALCON: Feedback-driven Adaptive Long/short-term memory reinforced Coding Optimization system](https://mlsanity.com/paper/2410.21349/) (2024)
- [Assessing Language Models' Worldview for Fiction Generation](https://mlsanity.com/paper/2408.07904/) (2024)
- [Generating Visual Stories with Grounded and Coreferent Characters](https://mlsanity.com/paper/2409.13555/) (2024)

## Built on by (most cited first, 30 of 42)

- [HUD: Hierarchical Uncertainty-Aware Disambiguation Network for Composed Video Retrieval](https://mlsanity.com/paper/2512.02792/) (2025)
- [Advancing Sequential Numerical Prediction in Autoregressive Models](https://mlsanity.com/paper/2505.13077/) (2025)
- [ForgetMe: Evaluating Selective Forgetting in Generative Models](https://mlsanity.com/paper/2504.12574/) (2025)
- [Cross-Cloud Data Privacy Protection: Optimizing Collaborative Mechanisms of AI Systems by Integrating Federated Learning and LLMs](https://mlsanity.com/paper/2505.13292/) (2025)
- [Memory-Augmented Transformers: A Systematic Review from Neuroscience Principles to Enhanced Model Architectures](https://mlsanity.com/paper/2508.10824/) (2025)
- [User Behavior Analysis in Privacy Protection with Large Language Models: A Study on Privacy Preferences with Limited Data](https://mlsanity.com/paper/2505.06305/) (2025)
- [K2VAE: A Koopman-Kalman Enhanced Variational AutoEncoder for Probabilistic Time Series Forecasting](https://mlsanity.com/paper/2505.23017/) (2025)
- [RAG Security and Privacy: Formalizing the Threat Model and Attack Surface](https://mlsanity.com/paper/2509.20324/) (2025)
- [Research on Personalized Financial Product Recommendation by Integrating Large Language Models and Graph Neural Networks](https://mlsanity.com/paper/2506.05873/) (2025)
- [AI-Driven Prognostics for State of Health Prediction in Li-ion Batteries: A Comprehensive Analysis with Validation](https://mlsanity.com/paper/2504.05728/) (2025)
- [Overview of the NLPCC 2025 Shared Task 4: Multi-modal, Multilingual, and Multi-hop Medical Instructional Video Question Answering Challenge](https://mlsanity.com/paper/2505.06814/) (2025)
- [Meta-Learning for Cold-Start Personalization in Prompt-Tuned LLMs](https://mlsanity.com/paper/2507.16672/) (2025)
- [A Narrative Review on Large AI Models in Lung Cancer Screening, Diagnosis, and Treatment Planning](https://mlsanity.com/paper/2506.07236/) (2025)
- [A Survey of Link Prediction in N-ary Knowledge Graphs](https://mlsanity.com/paper/2506.08970/) (2025)
- [Deep Learning Model Acceleration and Optimization Strategies for Real-Time Recommendation Systems](https://mlsanity.com/paper/2506.11421/) (2025)
- [Coherent Multimodal Reasoning with Iterative Self-Evaluation for Vision-Language Models](https://mlsanity.com/paper/2508.02886/) (2025)
- [Re:Verse -- Can Your VLM Read a Manga?](https://mlsanity.com/paper/2508.08508/) (2025)
- [Knowledge-Augmented Language Models Interpreting Structured Chest X-Ray Findings](https://mlsanity.com/paper/2505.01711/) (2025)
- [Human-AI Co-Creation: A Framework for Collaborative Design in Intelligent Systems](https://mlsanity.com/paper/2507.17774/) (2025)
- [The Structural Scalpel: Automated Contiguous Layer Pruning for Large Language Models](https://mlsanity.com/paper/2510.23652/) (2025)
- [Can LLM Agents Stick to the Script? A Benchmark for Long-Horizon Consistency in Interactive Narratives](https://mlsanity.com/paper/2608.08160/) (2026)
- [Federated Learning-Based Data Collaboration Method for Enhancing Edge Cloud AI System Security Using Large Language Models](https://mlsanity.com/paper/2506.18087/) (2025)
- [Large Language Models for Zero-Shot Multicultural Name Recognition](https://mlsanity.com/paper/2507.04149/) (2025)
- [CAP-LLM: Context-Augmented Personalized Large Language Models for News Headline Generation](https://mlsanity.com/paper/2508.03935/) (2025)
- [Coarse-to-Fine Personalized LLM Impressions for Streamlined Radiology Reports](https://mlsanity.com/paper/2508.15845/) (2025)
- [Context-Aware Multi-Turn Visual-Textual Reasoning in LVLMs via Dynamic Memory and Adaptive Visual Guidance](https://mlsanity.com/paper/2509.05669/) (2025)
- [Spoiler Alert: Narrative Forecasting as a Metric for Tension in LLM Storytelling](https://mlsanity.com/paper/2604.09854/) (2026)
- [Revolutionizing Radiology Workflow with Factual and Efficient CXR Report Generation](https://mlsanity.com/paper/2506.01118/) (2025)
- [Unlocking Compositional Control: Self-Supervision for LVLM-Based Image Generation](https://mlsanity.com/paper/2507.04151/) (2025)
- [VL-MedGuide: A Visual-Linguistic Large Model for Intelligent and Explainable Skin Disease Auxiliary Diagnosis](https://mlsanity.com/paper/2508.06624/) (2025)

## Abstract (arXiv)

Large Language Models (LLMs) can generate creative and engaging narratives from user-specified input, but maintaining coherence and emotional depth throughout these AI-generated stories remains a challenge. In this work, we propose SCORE, a framework for Story Coherence and Retrieval Enhancement, designed to detect and resolve narrative inconsistencies. By tracking key item statuses and generating episode summaries, SCORE uses a Retrieval-Augmented Generation (RAG) approach to identify related episodes and enhance the overall story structure. Experimental results from testing multiple LLM-generated stories demonstrate that SCORE significantly improves the consistency and stability of narrative coherence compared to baseline GPT models, providing a more robust method for evaluating and refining AI-generated narratives.