# Reference-Aware Language Models

arXiv: https://arxiv.org/abs/1611.01628 · HTML: https://mlsanity.com/paper/1611.01628/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Nov 2016.

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

- [Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMs](https://mlsanity.com/paper/2210.13312/) (2022)
- [Chart-to-Text: A Large-Scale Benchmark for Chart Summarization](https://mlsanity.com/paper/2203.06486/) (2022)
- [OpenCQA: Open-ended Question Answering with Charts](https://mlsanity.com/paper/2210.06628/) (2022)
- [Relational Memory Augmented Language Models](https://mlsanity.com/paper/2201.09680/) (2022)
- [Innovations in Neural Data-to-text Generation: A Survey](https://mlsanity.com/paper/2207.12571/) (2022)
- [Markovian Transformers for Informative Language Modeling](https://mlsanity.com/paper/2404.18988/) (2024)
- [Assorted, Archetypal and Annotated Two Million (3A2M) Cooking Recipes Dataset based on Active Learning](https://mlsanity.com/paper/2303.16778/) (2023)
- [CoreLM: Coreference-aware Language Model Fine-Tuning](https://mlsanity.com/paper/2111.02687/) (2021)

## Abstract (arXiv)

We propose a general class of language models that treat reference as an explicit stochastic latent variable. This architecture allows models to create mentions of entities and their attributes by accessing external databases (required by, e.g., dialogue generation and recipe generation) and internal state (required by, e.g. language models which are aware of coreference). This facilitates the incorporation of information that can be accessed in predictable locations in databases or discourse context, even when the targets of the reference may be rare words. Experiments on three tasks shows our model variants based on deterministic attention.