# Facts2Story: Controlling Text Generation by Key Facts

arXiv: https://arxiv.org/abs/2012.04332 · HTML: https://mlsanity.com/paper/2012.04332/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Dec 2020.

## Built on by (most cited first, 7 of 7)

- [LongForm: Effective Instruction Tuning with Reverse Instructions](https://mlsanity.com/paper/2304.08460/) (2023)
- [Generate, Annotate, and Learn: NLP with Synthetic Text](https://mlsanity.com/paper/2106.06168/) (2021)
- [MOPO: Multi-Objective Prompt Optimization for Affective Text Generation](https://mlsanity.com/paper/2412.12948/) (2024)
- [Ontologically Faithful Generation of Non-Player Character Dialogues](https://mlsanity.com/paper/2212.10618/) (2022)
- [Has It All Been Solved? Open NLP Research Questions Not Solved by Large Language Models](https://mlsanity.com/paper/2305.12544/) (2023)
- [Event Transition Planning for Open-ended Text Generation](https://mlsanity.com/paper/2204.09453/) (2022)
- [Affective Natural Language Generation of Event Descriptions through Fine-grained Appraisal Conditions](https://mlsanity.com/paper/2307.14004/) (2023)

## Abstract (arXiv)

Recent advancements in self-attention neural network architectures have raised the bar for open-ended text generation. Yet, while current methods are capable of producing a coherent text which is several hundred words long, attaining control over the content that is being generated -- as well as evaluating it -- are still open questions. We propose a controlled generation task which is based on expanding a sequence of facts, expressed in natural language, into a longer narrative. We introduce human-based evaluation metrics for this task, as well as a method for deriving a large training dataset. We evaluate three methods on this task, based on fine-tuning pre-trained models. We show that while auto-regressive, unidirectional Language Models such as GPT2 produce better fluency, they struggle to adhere to the requested facts. We propose a plan-and-cloze model (using fine-tuned XLNet) which produces competitive fluency while adhering to the requested content.