# Controllable Text Generation for Open-Domain Creativity and Fairness

arXiv: https://arxiv.org/abs/2209.12099 · HTML: https://mlsanity.com/paper/2209.12099/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 45 references that are in the map.
- First posted on arXiv 24 Sep 2022.

## Builds on (most cited first, 24 of 24)

- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Language (Technology) is Power: A Critical Survey of "Bias" in NLP](https://mlsanity.com/paper/2005.14050/) (2020)
- [The Woman Worked as a Babysitter: On Biases in Language Generation](https://mlsanity.com/paper/1909.01326/) (2019)
- [Plan-And-Write: Towards Better Automatic Storytelling](https://mlsanity.com/paper/1811.05701/) (2018)
- [Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overview](https://mlsanity.com/paper/1912.11078/) (2019)
- [Strategies for Structuring Story Generation](https://mlsanity.com/paper/1902.01109/) (2019)
- [Towards Controllable Biases in Language Generation](https://mlsanity.com/paper/2005.00268/) (2020)
- [Cross-Sentence N-ary Relation Extraction with Graph LSTMs](https://mlsanity.com/paper/1708.03743/) (2017)
- [Content Planning for Neural Story Generation with Aristotelian Rescoring](https://mlsanity.com/paper/2009.09870/) (2020)
- [DEGREE: A Data-Efficient Generation-Based Event Extraction Model](https://mlsanity.com/paper/2108.12724/) (2021)
- [Event Representations for Automated Story Generation with Deep Neural Nets](https://mlsanity.com/paper/1706.01331/) (2017)
- [Joint Event and Temporal Relation Extraction with Shared Representations and Structured Prediction](https://mlsanity.com/paper/1909.05360/) (2019)
- [MERMAID: Metaphor Generation with Symbolism and Discriminative Decoding](https://mlsanity.com/paper/2103.06779/) (2021)
- [GATE: Graph Attention Transformer Encoder for Cross-lingual Relation and Event Extraction](https://mlsanity.com/paper/2010.03009/) (2020)
- [ECONET: Effective Continual Pretraining of Language Models for Event Temporal Reasoning](https://mlsanity.com/paper/2012.15283/) (2020)
- [Pun Generation with Surprise](https://mlsanity.com/paper/1904.06828/) (2019)
- [Document-level Entity-based Extraction as Template Generation](https://mlsanity.com/paper/2109.04901/) (2021)
- [R3: Reverse, Retrieve, and Rank for Sarcasm Generation with Commonsense Knowledge](https://mlsanity.com/paper/2004.13248/) (2020)
- [Metaphor Generation with Conceptual Mappings](https://mlsanity.com/paper/2106.01228/) (2021)
- [AmbiPun: Generating Humorous Puns with Ambiguous Context](https://mlsanity.com/paper/2205.01825/) (2022)
- [Domain Knowledge Empowered Structured Neural Net for End-to-End Event Temporal Relation Extraction](https://mlsanity.com/paper/2009.07373/) (2020)
- [Discourse-level Relation Extraction via Graph Pooling](https://mlsanity.com/paper/2101.00124/) (2021)
- [Learning A Unified Named Entity Tagger From Multiple Partially Annotated Corpora For Efficient Adaptation](https://mlsanity.com/paper/1909.11535/) (2019)
- ["Nice Try, Kiddo": Investigating Ad Hominems in Dialogue Responses](https://mlsanity.com/paper/2010.12820/) (2020)

## Built on by (most cited first, 6 of 6)

- [Iterative Zero-Shot LLM Prompting for Knowledge Graph Construction](https://mlsanity.com/paper/2307.01128/) (2023)
- [Text Generation: A Systematic Literature Review of Tasks, Evaluation, and Challenges](https://mlsanity.com/paper/2405.15604/) (2024)
- [Igniting Creative Writing in Small Language Models: LLM-as-a-Judge versus Multi-Agent Refined Rewards](https://mlsanity.com/paper/2508.21476/) (2025)
- [AMERICANO: Argument Generation with Discourse-driven Decomposition and Agent Interaction](https://mlsanity.com/paper/2310.20352/) (2023)
- [Sequentially Controlled Text Generation](https://mlsanity.com/paper/2301.02299/) (2023)
- [One Reference or Many? Rethinking Multi-Reference Training for Intermediate-Entropy Text Generation](https://mlsanity.com/paper/2609.22805/) (2026)

## Abstract (arXiv)

Recent advances in large pre-trained language models have demonstrated strong results in generating natural languages and significantly improved performances for many natural language generation (NLG) applications such as machine translation and text summarization. However, when the generation tasks are more open-ended and the content is under-specified, existing techniques struggle to generate long-term coherent and creative content. Moreover, the models exhibit and even amplify social biases that are learned from the training corpora. This happens because the generation models are trained to capture the surface patterns (i.e. sequences of words), instead of capturing underlying semantics and discourse structures, as well as background knowledge including social norms. In this paper, I introduce our recent works on controllable text generation to enhance the creativity and fairness of language generation models. We explore hierarchical generation and constrained decoding, with applications to creative language generation including story, poetry, and figurative languages, and bias mitigation for generation models.