# ASPIRO: Any-shot Structured Parsing-error-Induced ReprOmpting for Consistent Data-to-Text Generation

arXiv: https://arxiv.org/abs/2310.17877 · HTML: https://mlsanity.com/paper/2310.17877/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 42 references that are in the map.
- First posted on arXiv 27 Oct 2023.

## Builds on (most cited first, 19 of 19)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [BLEURT: Learning Robust Metrics for Text Generation](https://mlsanity.com/paper/2004.04696/) (2020)
- [DART: Open-Domain Structured Data Record to Text Generation](https://mlsanity.com/paper/2007.02871/) (2020)
- [Handling Divergent Reference Texts when Evaluating Table-to-Text Generation](https://mlsanity.com/paper/1906.01081/) (2019)
- [Language Models are Few-shot Multilingual Learners](https://mlsanity.com/paper/2109.07684/) (2021)
- [INFOTABS: Inference on Tables as Semi-structured Data](https://mlsanity.com/paper/2005.06117/) (2020)
- [Semantic Noise Matters for Neural Natural Language Generation](https://mlsanity.com/paper/1911.03905/) (2019)
- [JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs](https://mlsanity.com/paper/2106.10502/) (2021)
- [Evaluating Semantic Accuracy of Data-to-Text Generation with Natural Language Inference](https://mlsanity.com/paper/2011.10819/) (2020)
- [NUBIA: NeUral Based Interchangeability Assessor for Text Generation](https://mlsanity.com/paper/2004.14667/) (2020)
- [Neural Pipeline for Zero-Shot Data-to-Text Generation](https://mlsanity.com/paper/2203.16279/) (2022)
- [ASDOT: Any-Shot Data-to-Text Generation with Pretrained Language Models](https://mlsanity.com/paper/2210.04325/) (2022)
- [Scalable Micro-planned Generation of Discourse from Structured Data](https://mlsanity.com/paper/1810.02889/) (2018)
- [What Makes Data-to-Text Generation Hard for Pretrained Language Models?](https://mlsanity.com/paper/2205.11505/) (2022)
- [Sound Natural: Content Rephrasing in Dialog Systems](https://mlsanity.com/paper/2011.01993/) (2020)
- [Mind the Labels: Describing Relations in Knowledge Graphs With Pretrained Models](https://mlsanity.com/paper/2210.07373/) (2022)

## Built on by (most cited first, 2 of 2)

- [Ontology-Free General-Domain Knowledge Graph-to-Text Generation Dataset Synthesis using Large Language Model](https://mlsanity.com/paper/2409.07088/) (2024)
- [Benchmarking Concept-Spilling Across Languages in LLMs](https://mlsanity.com/paper/2601.12549/) (2026)

## Abstract (arXiv)

We present ASPIRO, an approach for structured data verbalisation into short template sentences in zero to few-shot settings. Unlike previous methods, our approach prompts large language models (LLMs) to directly produce entity-agnostic templates, rather than relying on LLMs to faithfully copy the given example entities, or validating/crafting the templates manually. We incorporate LLM re-prompting, triggered by algorithmic parsing checks, as well as the PARENT metric induced consistency validation to identify and rectify template generation problems in real-time. ASPIRO, compared to direct LLM output, averages 66% parsing error rate reduction in generated verbalisations of RDF triples on the DART dataset. Our best 5-shot text-davinci-003 setup, scoring BLEU of 50.62, METEOR of 45.16, BLEURT of 0.82, NUBIA of 0.87, and PARENT of 0.8962 on the Rel2Text dataset, competes effectively with recent fine-tuned pre-trained language models.