# Promoting Graph Awareness in Linearized Graph-to-Text Generation

arXiv: https://arxiv.org/abs/2012.15793 · HTML: https://mlsanity.com/paper/2012.15793/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Dec 2020.

## Built on by (most cited first, 14 of 14)

- [Structural Adapters in Pretrained Language Models for AMR-to-text Generation](https://mlsanity.com/paper/2103.09120/) (2021)
- [Open Domain Question Answering with A Unified Knowledge Interface](https://mlsanity.com/paper/2110.08417/) (2021)
- [SMATCH++: Standardized and Extended Evaluation of Semantic Graphs](https://mlsanity.com/paper/2305.06993/) (2023)
- [Revisiting Generative Commonsense Reasoning: A Pre-Ordering Approach](https://mlsanity.com/paper/2205.13183/) (2022)
- [Narrating Causal Graphs with Large Language Models](https://mlsanity.com/paper/2403.07118/) (2024)
- [Learning to Predict Concept Ordering for Common Sense Generation](https://mlsanity.com/paper/2309.06363/) (2023)
- [Curriculum-Based Self-Training Makes Better Few-Shot Learners for Data-to-Text Generation](https://mlsanity.com/paper/2206.02712/) (2022)
- [Survey of Abstract Meaning Representation: Then, Now, Future](https://mlsanity.com/paper/2505.03229/) (2025)
- [Syntax Controlled Knowledge Graph-to-Text Generation with Order and Semantic Consistency](https://mlsanity.com/paper/2207.00719/) (2022)
- [Knowledge Graph for NLG in the context of conversational agents](https://mlsanity.com/paper/2307.01548/) (2023)
- [Can Knowledge Graphs Simplify Text?](https://mlsanity.com/paper/2308.06975/) (2023)
- [Evaluating and Improving Graph to Text Generation with Large Language Models](https://mlsanity.com/paper/2501.14497/) (2025)
- [What Gets Unmasked First? Trajectory Analysis of Diffusion Models for Graph-to-Text Generation](https://mlsanity.com/paper/2605.31564/) (2026)
- [Graph Evidence Is Not Enough: Diagnosing Native Decoder Use in Graph-Augmented LLMs](https://mlsanity.com/paper/2608.30437/) (2026)

## Abstract (arXiv)

Generating text from structured inputs, such as meaning representations or RDF triples, has often involved the use of specialized graph-encoding neural networks. However, recent applications of pretrained transformers to linearizations of graph inputs have yielded state-of-the-art generation results on graph-to-text tasks. Here, we explore the ability of these linearized models to encode local graph structures, in particular their invariance to the graph linearization strategy and their ability to reconstruct corrupted inputs. Our findings motivate solutions to enrich the quality of models' implicit graph encodings via scaffolding. Namely, we use graph-denoising objectives implemented in a multi-task text-to-text framework. We find that these denoising scaffolds lead to substantial improvements in downstream generation in low-resource settings.