# Control-DAG: Constrained Decoding for Non-Autoregressive Directed Acyclic T5 using Weighted Finite State Automata

arXiv: https://arxiv.org/abs/2404.06854 · HTML: https://mlsanity.com/paper/2404.06854/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 21 references that are in the map.
- First posted on arXiv 10 Apr 2024.

## Builds on (most cited first, 11 of 11)

- [BLEURT: Learning Robust Metrics for Text Generation](https://mlsanity.com/paper/2004.04696/) (2020)
- [Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Dataset](https://mlsanity.com/paper/1909.05855/) (2019)
- [Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translation](https://mlsanity.com/paper/1804.06609/) (2018)
- [DART: Open-Domain Structured Data Record to Text Generation](https://mlsanity.com/paper/2007.02871/) (2020)
- [Glancing Transformer for Non-Autoregressive Neural Machine Translation](https://mlsanity.com/paper/2008.07905/) (2020)
- [Directed Acyclic Transformer for Non-Autoregressive Machine Translation](https://mlsanity.com/paper/2205.07459/) (2022)
- [Guided Generation of Cause and Effect](https://mlsanity.com/paper/2107.09846/) (2021)
- [Viterbi Decoding of Directed Acyclic Transformer for Non-Autoregressive Machine Translation](https://mlsanity.com/paper/2210.05193/) (2022)
- [Fuzzy Alignments in Directed Acyclic Graph for Non-Autoregressive Machine Translation](https://mlsanity.com/paper/2303.06662/) (2023)
- [Directed Acyclic Transformer Pre-training for High-quality Non-autoregressive Text Generation](https://mlsanity.com/paper/2304.11791/) (2023)
- [Schema-Guided Semantic Accuracy: Faithfulness in Task-Oriented Dialogue Response Generation](https://mlsanity.com/paper/2301.12568/) (2023)

## Built on by (most cited first, 1 of 1)

- [From System 1 to System 2: A Survey of Reasoning Large Language Models](https://mlsanity.com/paper/2502.17419/) (2025)

## Abstract (arXiv)

The Directed Acyclic Transformer is a fast non-autoregressive (NAR) model that performs well in Neural Machine Translation. Two issues prevent its application to general Natural Language Generation (NLG) tasks: frequent Out-Of-Vocabulary (OOV) errors and the inability to faithfully generate entity names. We introduce Control-DAG, a constrained decoding algorithm for our Directed Acyclic T5 (DA-T5) model which offers lexical, vocabulary and length control. We show that Control-DAG significantly enhances DA-T5 on the Schema Guided Dialogue and the DART datasets, establishing strong NAR results for Task-Oriented Dialogue and Data-to-Text NLG.