# Global Autoregressive Models for Data-Efficient Sequence Learning

arXiv: https://arxiv.org/abs/1909.07063 · HTML: https://mlsanity.com/paper/1909.07063/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Sep 2019.

## Built on by (most cited first, 15 of 15)

- [COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics](https://mlsanity.com/paper/2202.11705/) (2022)
- [On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgetting](https://mlsanity.com/paper/2206.00761/) (2022)
- [RankGen: Improving Text Generation with Large Ranking Models](https://mlsanity.com/paper/2205.09726/) (2022)
- [Controlling Conditional Language Models without Catastrophic Forgetting](https://mlsanity.com/paper/2112.00791/) (2021)
- [Energy-Based Models for Code Generation under Compilability Constraints](https://mlsanity.com/paper/2106.04985/) (2021)
- [On-the-fly Preference Alignment via Principle-Guided Decoding](https://mlsanity.com/paper/2502.14204/) (2025)
- [Language Model Decoding as Direct Metrics Optimization](https://mlsanity.com/paper/2310.01041/) (2023)
- [A Block Metropolis-Hastings Sampler for Controllable Energy-based Text Generation](https://mlsanity.com/paper/2312.04510/) (2023)
- [Preference Optimization for Molecule Synthesis with Conditional Residual Energy-based Models](https://mlsanity.com/paper/2406.02066/) (2024)
- [disco: a toolkit for Distributional Control of Generative Models](https://mlsanity.com/paper/2303.05431/) (2023)
- [Sampling from Discrete Energy-Based Models with Quality/Efficiency Trade-offs](https://mlsanity.com/paper/2112.05702/) (2021)
- [Exploring Energy-based Language Models with Different Architectures and Training Methods for Speech Recognition](https://mlsanity.com/paper/2305.12676/) (2023)
- [Leveraging Importance Sampling to Detach Alignment Modules from Large Language Models](https://mlsanity.com/paper/2505.19700/) (2025)
- [Learning Globally Optimized Language Structure via Adversarial Training](https://mlsanity.com/paper/2311.06771/) (2023)
- [Entriever: Energy-based Retriever for Knowledge-Grounded Dialog Systems](https://mlsanity.com/paper/2506.00585/) (2025)

## Abstract (arXiv)

Standard autoregressive seq2seq models are easily trained by max-likelihood, but tend to show poor results under small-data conditions. We introduce a class of seq2seq models, GAMs (Global Autoregressive Models), which combine an autoregressive component with a log-linear component, allowing the use of global textita priori features to compensate for lack of data. We train these models in two steps. In the first step, we obtain an unnormalized GAM that maximizes the likelihood of the data, but is improper for fast inference or evaluation. In the second step, we use this GAM to train (by distillation) a second autoregressive model that approximates the normalized distribution associated with the GAM, and can be used for fast inference and evaluation. Our experiments focus on language modelling under synthetic conditions and show a strong perplexity reduction of using the second autoregressive model over the standard one.