# Towards Coherent and Consistent Use of Entities in Narrative Generation

arXiv: https://arxiv.org/abs/2202.01709 · HTML: https://mlsanity.com/paper/2202.01709/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 43 references that are in the map.
- First posted on arXiv 3 Feb 2022.

## Builds on (most cited first, 20 of 20)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [Plug and Play Language Models: A Simple Approach to Controlled Text Generation](https://mlsanity.com/paper/1912.02164/) (2019)
- [CTRL: A Conditional Transformer Language Model for Controllable Generation](https://mlsanity.com/paper/1909.05858/) (2019)
- [Compressive Transformers for Long-Range Sequence Modelling](https://mlsanity.com/paper/1911.05507/) (2019)
- [The NarrativeQA Reading Comprehension Challenge](https://mlsanity.com/paper/1712.07040/) (2017)
- [All That's 'Human' Is Not Gold: Evaluating Human Evaluation of Generated Text](https://mlsanity.com/paper/2107.00061/) (2021)
- [AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts](https://mlsanity.com/paper/2010.15980/) (2020)
- [Higher-order Coreference Resolution with Coarse-to-fine Inference](https://mlsanity.com/paper/1804.05392/) (2018)
- [Strategies for Structuring Story Generation](https://mlsanity.com/paper/1902.01109/) (2019)
- [PlotMachines: Outline-Conditioned Generation with Dynamic Plot State Tracking](https://mlsanity.com/paper/2004.14967/) (2020)
- [Content Planning for Neural Story Generation with Aristotelian Rescoring](https://mlsanity.com/paper/2009.09870/) (2020)
- [MEGATRON-CNTRL: Controllable Story Generation with External Knowledge Using Large-Scale Language Models](https://mlsanity.com/paper/2010.00840/) (2020)
- [Tracking the World State with Recurrent Entity Networks](https://mlsanity.com/paper/1612.03969/) (2016)
- [Dynamic Entity Representations in Neural Language Models](https://mlsanity.com/paper/1708.00781/) (2017)
- [Consistency and Coherency Enhanced Story Generation](https://mlsanity.com/paper/2010.08822/) (2020)
- [Exploiting the Bipartite Structure of Entity Grids for Document Coherence and Retrieval](https://mlsanity.com/paper/1608.00758/) (2016)

## Built on by (most cited first, 10 of 10)

- [Co-Writing Screenplays and Theatre Scripts with Language Models: An Evaluation by Industry Professionals](https://mlsanity.com/paper/2209.14958/) (2022)
- [Model Criticism for Long-Form Text Generation](https://mlsanity.com/paper/2210.08444/) (2022)
- [Beyond Multi-Token Prediction: Pretraining LLMs with Future Summaries](https://mlsanity.com/paper/2510.14751/) (2025)
- [MoPS: Modular Story Premise Synthesis for Open-Ended Automatic Story Generation](https://mlsanity.com/paper/2406.05690/) (2024)
- [Revisiting the Architectures like Pointer Networks to Efficiently Improve the Next Word Distribution, Summarization Factuality, and Beyond](https://mlsanity.com/paper/2305.12289/) (2023)
- [Frankentext: Stitching random text fragments into long-form narratives](https://mlsanity.com/paper/2505.18128/) (2025)
- [Generating Coherent Narratives by Learning Dynamic and Discrete Entity States with a Contrastive Framework](https://mlsanity.com/paper/2208.03985/) (2022)
- [SkyScript-100M: 1,000,000,000 Pairs of Scripts and Shooting Scripts for Short Drama](https://mlsanity.com/paper/2408.09333/) (2024)
- [Emo Pillars: Knowledge Distillation to Support Fine-Grained Context-Aware and Context-Less Emotion Classification](https://mlsanity.com/paper/2504.16856/) (2025)
- [MET-Bench: Multimodal Entity Tracking for Evaluating the Limitations of Vision-Language and Reasoning Models](https://mlsanity.com/paper/2502.10886/) (2025)

## Abstract (arXiv)

Large pre-trained language models (LMs) have demonstrated impressive capabilities in generating long, fluent text; however, there is little to no analysis on their ability to maintain entity coherence and consistency. In this work, we focus on the end task of narrative generation and systematically analyse the long-range entity coherence and consistency in generated stories. First, we propose a set of automatic metrics for measuring model performance in terms of entity usage. Given these metrics, we quantify the limitations of current LMs. Next, we propose augmenting a pre-trained LM with a dynamic entity memory in an end-to-end manner by using an auxiliary entity-related loss for guiding the reads and writes to the memory. We demonstrate that the dynamic entity memory increases entity coherence according to both automatic and human judgment and helps preserving entity-related information especially in settings with a limited context window. Finally, we also validate that our automatic metrics are correlated with human ratings and serve as a good indicator of the quality of generated stories.