# Dynamic Entity Representations in Neural Language Models

arXiv: https://arxiv.org/abs/1708.00781 · HTML: https://mlsanity.com/paper/1708.00781/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Aug 2017.

## Built on by (most cited first, 19 of 19)

- [Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMs](https://mlsanity.com/paper/2210.13312/) (2022)
- [Entity Structure Within and Throughout: Modeling Mention Dependencies for Document-Level Relation Extraction](https://mlsanity.com/paper/2102.10249/) (2021)
- [Entity Tracking in Language Models](https://mlsanity.com/paper/2305.02363/) (2023)
- [Automatic Story Generation: Challenges and Attempts](https://mlsanity.com/paper/2102.12634/) (2021)
- [Relational Memory Augmented Language Models](https://mlsanity.com/paper/2201.09680/) (2022)
- [Robust Pronoun Fidelity with English LLMs: Are they Reasoning, Repeating, or Just Biased?](https://mlsanity.com/paper/2404.03134/) (2024)
- [Persona-Guided Planning for Controlling the Protagonist's Persona in Story Generation](https://mlsanity.com/paper/2204.10703/) (2022)
- [Towards Coherent and Consistent Use of Entities in Narrative Generation](https://mlsanity.com/paper/2202.01709/) (2022)
- [Paired Examples as Indirect Supervision in Latent Decision Models](https://mlsanity.com/paper/2104.01759/) (2021)
- [Generating Coherent Narratives by Learning Dynamic and Discrete Entity States with a Contrastive Framework](https://mlsanity.com/paper/2208.03985/) (2022)
- [Does Entity Abstraction Help Generative Transformers Reason?](https://mlsanity.com/paper/2201.01787/) (2022)
- [Weakly Supervised Reasoning by Neuro-Symbolic Approaches](https://mlsanity.com/paper/2309.13072/) (2023)
- [Stick to Facts: Towards Fidelity-oriented Product Description Generation](https://mlsanity.com/paper/2503.08454/) (2025)
- [Changing the Narrative Perspective: From Deictic to Anaphoric Point of View](https://mlsanity.com/paper/2103.04176/) (2021)
- [Modeling Human Mental States with an Entity-based Narrative Graph](https://mlsanity.com/paper/2104.07079/) (2021)
- [Measuring Context-Word Biases in Lexical Semantic Datasets](https://mlsanity.com/paper/2112.06733/) (2021)
- [A Data Source for Reasoning Embodied Agents](https://mlsanity.com/paper/2309.07974/) (2023)
- [CoreLM: Coreference-aware Language Model Fine-Tuning](https://mlsanity.com/paper/2111.02687/) (2021)
- [A Benchmark for Understanding and Generating Dialogue between Characters in Stories](https://mlsanity.com/paper/2209.08524/) (2022)

## Abstract (arXiv)

Understanding a long document requires tracking how entities are introduced and evolve over time. We present a new type of language model, EntityNLM, that can explicitly model entities, dynamically update their representations, and contextually generate their mentions. Our model is generative and flexible; it can model an arbitrary number of entities in context while generating each entity mention at an arbitrary length. In addition, it can be used for several different tasks such as language modeling, coreference resolution, and entity prediction. Experimental results with all these tasks demonstrate that our model consistently outperforms strong baselines and prior work.