# disco: a toolkit for Distributional Control of Generative Models

arXiv: https://arxiv.org/abs/2303.05431 · HTML: https://mlsanity.com/paper/2303.05431/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 36 references that are in the map.
- First posted on arXiv 8 Mar 2023.

## Builds on (most cited first, 28 of 28)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Scaling Autoregressive Models for Content-Rich Text-to-Image Generation](https://mlsanity.com/paper/2206.10789/) (2022)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [A General Language Assistant as a Laboratory for Alignment](https://mlsanity.com/paper/2112.00861/) (2021)
- [Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond](https://mlsanity.com/paper/1602.06023/) (2016)
- [Recipes for building an open-domain chatbot](https://mlsanity.com/paper/2004.13637/) (2020)
- [Datasets: A Community Library for Natural Language Processing](https://mlsanity.com/paper/2109.02846/) (2021)
- [Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization](https://mlsanity.com/paper/2210.01241/) (2022)
- [Generative Spoken Dialogue Language Modeling](https://mlsanity.com/paper/2203.16502/) (2022)
- [Aligning Language Models with Preferences through f-divergence Minimization](https://mlsanity.com/paper/2302.08215/) (2023)
- [A Distributional Approach to Controlled Text Generation](https://mlsanity.com/paper/2012.11635/) (2020)
- [Entity-level Factual Consistency of Abstractive Text Summarization](https://mlsanity.com/paper/2102.09130/) (2021)
- [On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgetting](https://mlsanity.com/paper/2206.00761/) (2022)
- [Language Models are Few-shot Learners for Prognostic Prediction](https://mlsanity.com/paper/2302.12692/) (2023)
- [Theory-Grounded Measurement of U.S. Social Stereotypes in English Language Models](https://mlsanity.com/paper/2206.11684/) (2022)
- [Controlling Conditional Language Models without Catastrophic Forgetting](https://mlsanity.com/paper/2112.00791/) (2021)
- [Distributional Reinforcement Learning for Energy-Based Sequential Models](https://mlsanity.com/paper/1912.08517/) (2019)
- [Global Autoregressive Models for Data-Efficient Sequence Learning](https://mlsanity.com/paper/1909.07063/) (2019)
- [Energy-Based Models for Code Generation under Compilability Constraints](https://mlsanity.com/paper/2106.04985/) (2021)

## Built on by (most cited first, 3 of 3)

- [Negating Negatives: Alignment with Human Negative Samples via Distributional Dispreference Optimization](https://mlsanity.com/paper/2403.03419/) (2024)
- [Guaranteed Generation from Large Language Models](https://mlsanity.com/paper/2410.06716/) (2024)
- [Composable Decoding on the Probability Simplex: Theory and Implementation](https://mlsanity.com/paper/2609.34992/) (2026)

## Abstract (arXiv)

Pre-trained language models and other generative models have revolutionized NLP and beyond. However, these models tend to reproduce undesirable biases present in their training data. Also, they may overlook patterns that are important but challenging to capture. To address these limitations, researchers have introduced distributional control techniques. These techniques, not limited to language, allow controlling the prevalence (i.e., expectations) of any features of interest in the model's outputs. Despite their potential, the widespread adoption of these techniques has been hindered by the difficulty in adapting complex, disconnected code. Here, we present disco, an open-source Python library that brings these techniques to the broader public.