# A Plug-and-Play Method for Controlled Text Generation

arXiv: https://arxiv.org/abs/2109.09707 · HTML: https://mlsanity.com/paper/2109.09707/

## Key facts

- Cited by 56 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 46 references that are in the map.
- First posted on arXiv 20 Sep 2021.

## Builds on (most cited first, 29 of 29)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation](https://mlsanity.com/paper/1609.08144/) (2016)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [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)
- [Neural Text Generation with Unlikelihood Training](https://mlsanity.com/paper/1908.04319/) (2019)
- [A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Stories](https://mlsanity.com/paper/1604.01696/) (2016)
- [GeDi: Generative Discriminator Guided Sequence Generation](https://mlsanity.com/paper/2009.06367/) (2020)
- [SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient](https://mlsanity.com/paper/1609.05473/) (2016)
- [FUDGE: Controlled Text Generation With Future Discriminators](https://mlsanity.com/paper/2104.05218/) (2021)
- [How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation](https://mlsanity.com/paper/1603.08023/) (2016)
- [Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search](https://mlsanity.com/paper/1704.07138/) (2017)
- [Plan-And-Write: Towards Better Automatic Storytelling](https://mlsanity.com/paper/1811.05701/) (2018)
- [Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translation](https://mlsanity.com/paper/1804.06609/) (2018)
- [Correcting Length Bias in Neural Machine Translation](https://mlsanity.com/paper/1808.10006/) (2018)
- [Learning to Write with Cooperative Discriminators](https://mlsanity.com/paper/1805.06087/) (2018)
- [If beam search is the answer, what was the question?](https://mlsanity.com/paper/2010.02650/) (2020)
- [CGMH: Constrained Sentence Generation by Metropolis-Hastings Sampling](https://mlsanity.com/paper/1811.10996/) (2018)
- [MEGATRON-CNTRL: Controllable Story Generation with External Knowledge Using Large-Scale Language Models](https://mlsanity.com/paper/2010.00840/) (2020)
- [Sparse Text Generation](https://mlsanity.com/paper/2004.02644/) (2020)
- [Backward and Forward Language Modeling for Constrained Sentence Generation](https://mlsanity.com/paper/1512.06612/) (2015)
- [Keyphrase Cloud Generation of Broadcast News](https://mlsanity.com/paper/1306.4606/) (2013)
- [Changing the Mind of Transformers for Topically-Controllable Language Generation](https://mlsanity.com/paper/2103.15335/) (2021)

## Built on by (most cited first, 30 of 56)

- [Generating Training Data with Language Models: Towards Zero-Shot Language Understanding](https://mlsanity.com/paper/2202.04538/) (2022)
- [SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Control](https://mlsanity.com/paper/2210.17432/) (2022)
- [A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Models](https://mlsanity.com/paper/2201.05337/) (2022)
- [Pretrained Language Models for Text Generation: A Survey](https://mlsanity.com/paper/2201.05273/) (2022)
- [Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey](https://mlsanity.com/paper/2210.07700/) (2022)
- [Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model](https://mlsanity.com/paper/2310.09520/) (2023)
- [Of Human Criteria and Automatic Metrics: A Benchmark of the Evaluation of Story Generation](https://mlsanity.com/paper/2208.11646/) (2022)
- [Gradient-Based Constrained Sampling from Language Models](https://mlsanity.com/paper/2205.12558/) (2022)
- [DFX: A Low-latency Multi-FPGA Appliance for Accelerating Transformer-based Text Generation](https://mlsanity.com/paper/2209.10797/) (2022)
- [Syntactic and Semantic Control of Large Language Models via Sequential Monte Carlo](https://mlsanity.com/paper/2504.13139/) (2025)
- [Tuning Language Models as Training Data Generators for Augmentation-Enhanced Few-Shot Learning](https://mlsanity.com/paper/2211.03044/) (2022)
- [Gradient-Based Language Model Red Teaming](https://mlsanity.com/paper/2401.16656/) (2024)
- [Controllable Mixed-Initiative Dialogue Generation through Prompting](https://mlsanity.com/paper/2305.04147/) (2023)
- [Elastic Weight Removal for Faithful and Abstractive Dialogue Generation](https://mlsanity.com/paper/2303.17574/) (2023)
- [Mixture of Soft Prompts for Controllable Data Generation](https://mlsanity.com/paper/2303.01580/) (2023)
- [Open-world Story Generation with Structured Knowledge Enhancement: A Comprehensive Survey](https://mlsanity.com/paper/2212.04634/) (2022)
- [Learning to Simulate Natural Language Feedback for Interactive Semantic Parsing](https://mlsanity.com/paper/2305.08195/) (2023)
- [Generalists vs. Specialists: Evaluating LLMs on Highly-Constrained Biophysical Sequence Optimization Tasks](https://mlsanity.com/paper/2410.22296/) (2024)
- [Integrating Vectorized Lexical Constraints for Neural Machine Translation](https://mlsanity.com/paper/2203.12210/) (2022)
- [Most Language Models can be Poets too: An AI Writing Assistant and Constrained Text Generation Studio](https://mlsanity.com/paper/2306.15926/) (2023)
- [Two Heads Are Better Than One: Integrating Knowledge from Knowledge Graphs and Large Language Models for Entity Alignment](https://mlsanity.com/paper/2401.16960/) (2024)
- ["What makes a question inquisitive?" A Study on Type-Controlled Inquisitive Question Generation](https://mlsanity.com/paper/2205.08056/) (2022)
- [Speaking the Language of Your Listener: Audience-Aware Adaptation via Plug-and-Play Theory of Mind](https://mlsanity.com/paper/2305.19933/) (2023)
- [Large Language Models can be Strong Self-Detoxifiers](https://mlsanity.com/paper/2410.03818/) (2024)
- [Creativity in AI: Progresses and Challenges](https://mlsanity.com/paper/2410.17218/) (2024)
- [The Achilles' Heel of LLMs: How Altering a Handful of Neurons Can Cripple Language Abilities](https://mlsanity.com/paper/2510.10238/) (2025)
- [Plug-and-Play Document Modules for Pre-trained Models](https://mlsanity.com/paper/2305.17660/) (2023)
- [Emotion-Conditioned Text Generation through Automatic Prompt Optimization](https://mlsanity.com/paper/2308.04857/) (2023)
- [Paired Autoencoders for Likelihood-free Estimation in Inverse Problems](https://mlsanity.com/paper/2405.13220/) (2024)
- [FreeCtrl: Constructing Control Centers with Feedforward Layers for Learning-Free Controllable Text Generation](https://mlsanity.com/paper/2406.09688/) (2024)

## Abstract (arXiv)

Large pre-trained language models have repeatedly shown their ability to produce fluent text. Yet even when starting from a prompt, generation can continue in many plausible directions. Current decoding methods with the goal of controlling generation, e.g., to ensure specific words are included, either require additional models or fine-tuning, or work poorly when the task at hand is semantically unconstrained, e.g., story generation. In this work, we present a plug-and-play decoding method for controlled language generation that is so simple and intuitive, it can be described in a single sentence: given a topic or keyword, we add a shift to the probability distribution over our vocabulary towards semantically similar words. We show how annealing this distribution can be used to impose hard constraints on language generation, something no other plug-and-play method is currently able to do with SOTA language generators. Despite the simplicity of this approach, we see it works incredibly well in practice: decoding from GPT-2 leads to diverse and fluent sentences while guaranteeing the appearance of given guide words. We perform two user studies, revealing that (1) our method outperforms competing methods in human evaluations; and (2) forcing the guide words to appear in the generated text has no impact on the fluency of the generated text.