# AI-Assisted Authoring for Transparent, Data-Driven Documents

arXiv: https://arxiv.org/abs/2601.06027 · HTML: https://mlsanity.com/paper/2601.06027/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 43 references that are in the map.
- First posted on arXiv 27 Oct 2025.

## Builds on (most cited first, 17 of 17)

- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Parsing Argumentation Structures in Persuasive Essays](https://mlsanity.com/paper/1604.07370/) (2016)
- [JFLEG: A Fluency Corpus and Benchmark for Grammatical Error Correction](https://mlsanity.com/paper/1702.04066/) (2017)
- [ChatGPT or Grammarly? Evaluating ChatGPT on Grammatical Error Correction Benchmark](https://mlsanity.com/paper/2303.13648/) (2023)
- [SciFIBench: Benchmarking Large Multimodal Models for Scientific Figure Interpretation](https://mlsanity.com/paper/2405.08807/) (2024)
- [Can LLM feedback enhance review quality? A randomized study of 20K reviews at ICLR 2025](https://mlsanity.com/paper/2504.09737/) (2025)
- [Errors are Useful Prompts: Instruction Guided Task Programming with Verifier-Assisted Iterative Prompting](https://mlsanity.com/paper/2303.14100/) (2023)
- [AI-Driven Review Systems: Evaluating LLMs in Scalable and Bias-Aware Academic Reviews](https://mlsanity.com/paper/2408.10365/) (2024)
- [Neural End-to-End Learning for Computational Argumentation Mining](https://mlsanity.com/paper/1704.06104/) (2017)
- [Can Large Language Models perform Relation-based Argument Mining?](https://mlsanity.com/paper/2402.11243/) (2024)
- [Sentence-State LSTM for Text Representation](https://mlsanity.com/paper/1805.02474/) (2018)
- [Argument Mining Driven Analysis of Peer-Reviews](https://mlsanity.com/paper/2012.07743/) (2020)
- [Smoke: Fine-grained Lineage at Interactive Speed](https://mlsanity.com/paper/1801.07237/) (2018)
- [When Reviewers Lock Horn: Finding Disagreement in Scientific Peer Reviews](https://mlsanity.com/paper/2310.18685/) (2023)
- [Linked visualisations via Galois dependencies](https://mlsanity.com/paper/2109.00445/) (2021)
- [Cognacy Queries over Dependence Graphs for Transparent Visualisations](https://mlsanity.com/paper/2403.04403/) (2024)
- [Meaning Beyond Truth Conditions: Evaluating Discourse Level Understanding via Anaphora Accessibility](https://mlsanity.com/paper/2502.14119/) (2025)

## Abstract (arXiv)

We introduce _transparent documents_, interactive web-based scholarly articles which allow readers to explore the relationship to the underlying data by hovering over fragments of text, and present an LLM-based tool for authoring transparent documents, building on recent developments in data provenance for general-purpose programming languages. As a target platform, our implementation uses Fluid, an open source programming language with a provenance-tracking runtime. Our agent-based tool supports a human author during the creation of transparent documents, identifying fragments of text which can be computed from data, such as numerical values selected from records or computed by aggregations like sum and mean, comparatives and superlatives like _better than_ and _largest_, trend-adjectives like _growing_, and similar quantitative or semi-quantitative phrases, and then attempts to synthesise a suitable Fluid query over the data which generates the target string. The resulting expression is inserted into the article's web page, turning the static text fragment into an interactable data-driven element able to reveal the data that underwrites the natural language claim. We evaluate our approach on a subset of SciGen, an open source dataset consisting of tables from scientific articles and their corresponding descriptions, which we extend with hand-generated counterfactual test cases to evaluate how well machine-generated expressions generalise. Our results show that gpt4o is often able to synthesise compound expressions extensionally compatible with our gold solutions.