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

TL;DR

This paper presents a hybrid human-in-the-loop framework for accessible text generation using large language models, enhancing transparency, accountability, and user-centered evaluation in text simplification.

Contribution

It introduces a novel hybrid framework that integrates human participation into LLM-based text simplification, including real-time adjustments and systematic review mechanisms.

Findings

Improved alignment with accessibility standards

Enhanced transparency and traceability in text generation

Effective human oversight improves model outputs

Abstract

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.