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

• URL: http://arxiv.org/abs/2603.18879v1
• Date: Thu, 19 Mar 2026 13:23:34 GMT
• Title: A Human-in/on-the-Loop Framework for Accessible Text Generation
• Abstract summary: This paper introduces a hybrid framework that explicitly integrates human participation into accessible text generation.<n>Human-in-the-Loop (HiTL) contributions guide adjustments during generation, while Human-on-the-Loop (HoTL) supervision ensures systematic post-generation review.
• Score: 0.7734726150561086
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• From Holistic Evaluation to Structured Criteria: Rubrics Across the Evolving LLM Landscape [79.30826980815927]
  rubrics are explicit criteria sets that transform complex quality judgments into structured and actionable standards.<n>We systematically organize existing rubric designs, examine their construction and optimization, and analyze their role across evaluation and training.
  arXiv  Detail & Related papers  (2026-06-07T13:34:55Z)
• A Practice Auditing Framework for Large Language Model Use: Collective Empiricism, Pseudo-Rational Cognition, and Governance of AI-Generated Content [9.414394075880033]
  This paper proposes a practice auditing framework for LLM use and AI-generated content governance.<n>The paper analyzes AI subjectivity illusion, subjectivity structures in input materials, template loops in AI-AI conversations, statistical misjudgment in AIGC detection, and memory pollution when generated content enters future contexts.
  arXiv  Detail & Related papers  (2026-06-02T00:46:47Z)
• Explainability and Certification of AI-Generated Educational Assessments [0.0]
  This chapter proposes a comprehensive framework for explainability and certification of AI-generated assessment items.<n>A structured certification metadata schema is introduced to capture provenance, alignment predictions, reviewer actions, and ethical indicators.<n>A proof-of-concept study on 500 AI-generated computer science questions demonstrates the framework's feasibility.
  arXiv  Detail & Related papers  (2026-03-18T11:33:58Z)
• Steering LLMs via Scalable Interactive Oversight [74.12746881843044]
  Large Language Models increasingly automate complex, long-horizon tasks such as emphvibe coding, a supervision gap has emerged.<n>It presents a critical challenge in scalable oversight: enabling humans to responsibly steer AI systems on tasks that surpass their own ability to specify or verify.
  arXiv  Detail & Related papers  (2026-02-04T04:52:00Z)
• RubricRL: Simple Generalizable Rewards for Text-to-Image Generation [48.51955133988087]
  Reinforcement learning (RL) has recently emerged as a promising approach for aligning text-to-image generative models with human preferences.<n>Existing methods often rely on either composite metrics (e.g., CLIP, OCR, and realism scores) with fixed weights or a single scalar reward distilled from human preference models.<n>We proposeRL, a simple and general framework for rubric-based reward design that offers greater interpretability, rubricsability, and user control.
  arXiv  Detail & Related papers  (2025-11-25T18:59:55Z)
• Toward Human-Centered Readability Evaluation [0.0]
  The Human-Centered Readability Score (HCRS) is a five-dimensional evaluation framework grounded in Human-Computer Interaction (HCI) and health communication research.<n>HCRS integrates automatic measures with structured human feedback to capture readability and contextual aspects of readability.<n>This work aims to advance the evaluation of health text simplification beyond surface metrics, enabling NLP systems that align more closely with diverse users' needs, expectations, and lived experiences.
  arXiv  Detail & Related papers  (2025-10-12T20:38:32Z)
• Taxonomy of User Needs and Actions [51.86289485979439]
  The growing ubiquity of conversational AI highlights the need for frameworks that capture users' instrumental goals and the situated, adaptive, and social practices through which they achieve them.<n>To address this gap, we introduce the Taxonomy of User Needs and Actions (TUNA), an empirically grounded framework developed through iterative qualitative analysis of 1193 human-AI conversations.<n> TUNA organizes user actions into a three-level hierarchy encompassing behaviors associated with information seeking, synthesis, procedural guidance, content creation, social interaction, and meta-conversation.
  arXiv  Detail & Related papers  (2025-10-07T17:04:42Z)
• Inclusive Easy-to-Read Generation for Individuals with Cognitive Impairments [2.1481398044731574]
  We introduce ETR-fr, the first dataset for ETR text generation fully compliant with European ETR guidelines.<n>We implement parameter-efficient fine-tuning on PLMs and LLMs to establish generative baselines.<n>Overall results show that PLMs perform comparably to LLMs and adapt effectively to out-of-domain texts.
  arXiv  Detail & Related papers  (2025-10-01T09:13:18Z)
• To Err Is Human; To Annotate, SILICON? Reducing Measurement Error in LLM Annotation [11.470318058523466]
  Large Language Models (LLMs) promise a cost-effective scalable alternative to human annotation.<n>We develop the SILICON methodology to systematically reduce measurement error from LLM annotation.<n>Our evidence indicates that reducing each error source is necessary, and that SILICON supports rigorous annotation in management research.
  arXiv  Detail & Related papers  (2024-12-19T02:21:41Z)
• CATER: Leveraging LLM to Pioneer a Multidimensional, Reference-Independent Paradigm in Translation Quality Evaluation [0.0]
  Comprehensive AI-assisted Translation Edit Ratio (CATER) is a novel framework for evaluating machine translation (MT) quality.<n>Uses large language models (LLMs) via a carefully designed prompt-based protocol.
  arXiv  Detail & Related papers  (2024-12-15T17:45:34Z)
• The Synergy of LLMs & RL Unlocks Offline Learning of Generalizable Language-Conditioned Policies with Low-fidelity Data [50.544186914115045]
  TEDUO is a novel training pipeline for offline language-conditioned policy learning in symbolic environments.<n>Our approach harnesses large language models (LLMs) in a dual capacity: first, as automatization tools augmenting offline datasets with richer annotations, and second, as generalizable instruction-following agents.
  arXiv  Detail & Related papers  (2024-12-09T18:43:56Z)
• Systematic Task Exploration with LLMs: A Study in Citation Text Generation [63.50597360948099]
  Large language models (LLMs) bring unprecedented flexibility in defining and executing complex, creative natural language generation (NLG) tasks. We propose a three-component research framework that consists of systematic input manipulation, reference data, and output measurement. We use this framework to explore citation text generation -- a popular scholarly NLP task that lacks consensus on the task definition and evaluation metric.
  arXiv  Detail & Related papers  (2024-07-04T16:41:08Z)
• Generating Summaries with Controllable Readability Levels [67.34087272813821]
  Several factors affect the readability level, such as the complexity of the text, its subject matter, and the reader's background knowledge. Current text generation approaches lack refined control, resulting in texts that are not customized to readers' proficiency levels. We develop three text generation techniques for controlling readability: instruction-based readability control, reinforcement learning to minimize the gap between requested and observed readability, and a decoding approach that uses look-ahead to estimate the readability of upcoming decoding steps.
  arXiv  Detail & Related papers  (2023-10-16T17:46:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.