# A Human-in/on-the-Loop Framework for Accessible Text Generation

arXiv: https://arxiv.org/abs/2603.18879 · HTML: https://mlsanity.com/paper/2603.18879/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 48 references that are in the map.
- First posted on arXiv 19 Mar 2026.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Can Large Language Models Be an Alternative to Human Evaluations?](https://mlsanity.com/paper/2305.01937/) (2023)
- [MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance](https://mlsanity.com/paper/1909.02622/) (2019)
- [Human-Centered Artificial Intelligence: Reliable, Safe & Trustworthy](https://mlsanity.com/paper/2002.04087/) (2020)
- [Better Rewards Yield Better Summaries: Learning to Summarise Without References](https://mlsanity.com/paper/1909.01214/) (2019)
- [LENS: A Learnable Evaluation Metric for Text Simplification](https://mlsanity.com/paper/2212.09739/) (2022)
- [Controllable Text Simplification with Explicit Paraphrasing](https://mlsanity.com/paper/2010.11004/) (2020)
- [Human-in-the-loop Artificial Intelligence](https://mlsanity.com/paper/1710.08191/) (2017)
- [Semantic Structural Evaluation for Text Simplification](https://mlsanity.com/paper/1810.05022/) (2018)
- [Exploring Large Language Models to generate Easy to Read content](https://mlsanity.com/paper/2407.20046/) (2024)
- [Enhancing Biomedical Lay Summarisation with External Knowledge Graphs](https://mlsanity.com/paper/2310.15702/) (2023)
- [Towards Trustworthy Lexical Simplification: Exploring Safety and Efficiency with Small LLMs](https://mlsanity.com/paper/2509.25086/) (2025)
- [Prompt-Based Simplification for Plain Language using Spanish Language Models](https://mlsanity.com/paper/2509.17209/) (2025)
- [Inclusive Easy-to-Read Generation for Individuals with Cognitive Impairments](https://mlsanity.com/paper/2510.00691/) (2025)

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

- [HULAT2 at MER-TRANS 2026: Governed Multi-Agent Simplification for Spanish Easy-to-Read Generation](https://mlsanity.com/paper/2607.02381/) (2026)

## Abstract (arXiv)

Plain Language and Easy-to-Read formats in text simplification are essential for cognitive accessibility. Yet current automatic simplification and evaluation pipelines remain largely automated, metric-driven, and fail to reflect user comprehension or normative standards. This paper introduces a hybrid framework that explicitly integrates human participation into LLM-based accessible text generation. Human-in-the-Loop (HiTL) contributions guide adjustments during generation, while Human-on-the-Loop (HoTL) supervision ensures systematic post-generation review. Empirical evidence from user studies and annotated resources is operationalized into (i) checklists aligned with standards, (ii) Event-Condition-Action trigger rules for activating expert oversight, and (iii) accessibility Key Performance Indicators (KPIs). The framework shows how human-centered mechanisms can be encoded for evaluation and reused to provide structured feedback that improves model adaptation. By embedding the human role in both generation and supervision, it establishes a traceable, reproducible, and auditable process for creating and evaluating accessible texts. In doing so, it integrates explainability and ethical accountability as core design principles, contributing to more transparent and inclusive NLP systems.