# PARENTing via Model-Agnostic Reinforcement Learning to Correct Pathological Behaviors in Data-to-Text Generation

arXiv: https://arxiv.org/abs/2010.10866 · HTML: https://mlsanity.com/paper/2010.10866/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Oct 2020.

## Built on by (most cited first, 4 of 4)

- [Controlling Hallucinations at Word Level in Data-to-Text Generation](https://mlsanity.com/paper/2102.02810/) (2021)
- [Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methods](https://mlsanity.com/paper/2203.05227/) (2022)
- [Innovations in Neural Data-to-text Generation: A Survey](https://mlsanity.com/paper/2207.12571/) (2022)
- [A Systematic Review of Data-to-Text NLG](https://mlsanity.com/paper/2402.08496/) (2024)

## Abstract (arXiv)

In language generation models conditioned by structured data, the classical training via maximum likelihood almost always leads models to pick up on dataset divergence (i.e., hallucinations or omissions), and to incorporate them erroneously in their own generations at inference. In this work, we build ontop of previous Reinforcement Learning based approaches and show that a model-agnostic framework relying on the recently introduced PARENT metric is efficient at reducing both hallucinations and omissions. Evaluations on the widely used WikiBIO and WebNLG benchmarks demonstrate the effectiveness of this framework compared to state-of-the-art models.