disco: a toolkit for Distributional Control of Generative Models
Not on the map. Why?
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.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 28 of its 36 references that are in the map. First posted on arXiv 8 Mar 2023.
Builds on
28 of 36 references.
References · 28
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
- 2022Training language models to follow instructions with human feedbackcited by 15,712
- 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
- 2021Evaluating Large Language Models Trained on Codecited by 8,053
- 2021Zero-Shot Text-to-Image Generationcited by 4,276
- 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
- 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
- 2019Fine-Tuning Language Models from Human Preferencescited by 2,124
- 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,287
- 2020RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Modelscited by 1,235
16 more
- 2021A General Language Assistant as a Laboratory for Alignmentcited by 1,023
- 2016Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyondcited by 809
- 2020Recipes for building an open-domain chatbotcited by 593
- 2021Datasets: A Community Library for Natural Language Processingcited by 526
- 2022Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimizationcited by 244
- 2022Generative Spoken Dialogue Language Modelingcited by 125
- 2021Entity-level Factual Consistency of Abstractive Text Summarizationcited by 118
- 2023Aligning Language Models with Preferences through f-divergence Minimizationcited by 118
- 2020A Distributional Approach to Controlled Text Generationcited by 117
- 2022On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgettingcited by 80
- 2023Language Models are Few-shot Learners for Prognostic Predictioncited by 37
- 2022Theory-Grounded Measurement of U.S. Social Stereotypes in English Language Modelscited by 35
- 2021Controlling Conditional Language Models without Catastrophic Forgettingcited by 32
- 2019Distributional Reinforcement Learning for Energy-Based Sequential Modelscited by 17
- 2019Global Autoregressive Models for Data-Efficient Sequence Learningcited by 15
- 2021Energy-Based Models for Code Generation under Compilability Constraintscited by 10
Built on by
Citing papers per year: 2024: 2; 2025: 0; 2026: 1.
3 papers.