# Efficient and Training-Free Control of Language Generation

arXiv: https://arxiv.org/abs/2205.06036 · HTML: https://mlsanity.com/paper/2205.06036/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 29 references that are in the map.
- First posted on arXiv 12 May 2022.

## Builds on (most cited first, 20 of 20)

- [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)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [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)
- [DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts](https://mlsanity.com/paper/2105.03023/) (2021)
- [GeDi: Generative Discriminator Guided Sequence Generation](https://mlsanity.com/paper/2009.06367/) (2020)
- [FUDGE: Controlled Text Generation With Future Discriminators](https://mlsanity.com/paper/2104.05218/) (2021)
- [A Neural Conversational Model](https://mlsanity.com/paper/1506.05869/) (2015)
- [NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics](https://mlsanity.com/paper/2112.08726/) (2021)
- [Raise a Child in Large Language Model: Towards Effective and Generalizable Fine-tuning](https://mlsanity.com/paper/2109.05687/) (2021)
- [Mix and Match: Learning-free Controllable Text Generation using Energy Language Models](https://mlsanity.com/paper/2203.13299/) (2022)
- [PowerTransformer: Unsupervised Controllable Revision for Biased Language Correction](https://mlsanity.com/paper/2010.13816/) (2020)
- [A Plug-and-Play Method for Controlled Text Generation](https://mlsanity.com/paper/2109.09707/) (2021)
- [Affect-LM: A Neural Language Model for Customizable Affective Text Generation](https://mlsanity.com/paper/1704.06851/) (2017)
- [Controllable Generation from Pre-trained Language Models via Inverse Prompting](https://mlsanity.com/paper/2103.10685/) (2021)
- [Directed Beam Search: Plug-and-Play Lexically Constrained Language Generation](https://mlsanity.com/paper/2012.15416/) (2020)
- [Softmax Tempering for Training Neural Machine Translation Models](https://mlsanity.com/paper/2009.09372/) (2020)

## Abstract (arXiv)

In recent years, there has been a growing interest in the development of language models capable of generating text with controllable attributes. While several approaches have been proposed, many of these methods require condition-specific data or significant computational resources. In this study, we propose a novel method called Gamma Sampling, which enables controllable language generation without the need for any training data and maintains a fast generation speed. Gamma Sampling incorporates attribute-related information into the sampling process, effectively guiding the language model to produce text with desired attributes. Our experimental results demonstrate that Gamma Sampling, when applied to GPT2, outperforms representative baselines in terms of diversity, attribute relevance, and overall quality of the generated samples.