Skip to content
Book Open access

DocuDebug: A Graph-Supported Interactive Editor for Verifying and Maintaining Internal Logical Consistency

Nov 2026 · ACM Symposium on User Interface Software and Technology · 0 citations · 78 references
Computer Science

TL;DR

DocuDebug, an interactive editor that reframes document verification as a software engineering task, is presented, demonstrating how structured visual diagnostics can shift AI-assisted writing from opaque global generation to systematic, user-controlled co-creation.

Abstract

While large language models (LLMs) accelerate report generation, maintaining logical consistency during revisions increases the cognitive load, and delegating this task to LLMs often results in unpredictable global overwrites. To address this, we present DocuDebug, an interactive editor that reframes document verification as a software engineering task. The system models a document’s logical structure and citations as an explicit dependency graph. Through a linter-like interface, users receive real-time warnings for logical conflicts and propagate localized edits with guided precision. In a within-subjects study with 12 professional writers, DocuDebug guided precise, necessary corrections, improving precision over threefold and reducing over-editing from over 40% to under 5%. Furthermore, objective logs revealed that users avoided blind acceptance, actively deliberating over each warning for nearly three minutes. This work demonstrates how structured visual diagnostics can shift AI-assisted writing from opaque global generation to systematic, user-controlled co-creation.

Read PDF

Similar papers

Open access Oct 2026

IncrConsist: Efficient Incremental Consistency Maintenance for LLM-Maintained Knowledge Bases

The results demonstrate that incremental affected-set computation—a classical technique in database materialization and ontology maintenance—can be adapted to LLM-maintained text knowledge bases, through extensions for typed provenance strength and lexical mutex conflict.

Bai-Ling Zhang · 0 citations
Book Open access Oct 2026

Typed Edits, Reviewable Models: Toward LLM-Supported Blended Co-Modeling

LLM-supported blended co-modeling is proposed: a semantic-delta protocol in which LLMs submit versioned, typed edit proposals to a modeling kernel instead of mutating models directly, which evaluates protocol executability and failure containment, not LLM or human effectiveness.

Federico Ciccozzi · 0 citations
Open access 2026

Seamless: Self-Maintaining Knowledge Graph Memory for Retrieval-Augmented Language Models

Large language model (LLM) agents have bounded context windows and therefore need external storage to retain knowledge across long interactions. Keeping that knowledge consistent requires reconciling changing facts, duplicate mentions, and competing retrieval priorities. We present Seamless, a self-maintaining knowledg...

Nikita Smirnov · 0 citations
#natural language process... Preprint Oct 2026

Structured Composition of Verifiable Atomic Insights for Table-to-Report Generation

Table-to-report generation refers to the task of automatically generating article-level analyt- ical reports from relational tables and is an essential capability for automated data science and decision support. Its central challenge lies in systematically discovering verifiable com- posite insights across tables, attr...

Teng Lin, Xin-Yu Liu, Nan Tang · 1 citation
Review Oct 2026

LogicTree: Object-Oriented Writing for Structured Human-AI Academic Authoring

Object-oriented writing (OOW), an OOD-inspired representation and interaction paradigm in which persistent writing objects serve as shared, manipulable referents for authors and AI, is proposed in LogicTree, an Overleaf-integrated prototype that combines a hierarchical object representation with a structure-grounded wr...

Jia-Jun Zhu, Xin-Yu Cheng, Wen-Shuo Zhang et al. · 0 citations
Book Open access Nov 2026

Great Grave: Modeling Versioned Context Units for Longitudinal LLM Interaction

This work presents Great Grave, a system that transforms LLM chat logs into Research Workflow Graphs, a system that segments conversations into intent-driven Context Units, groups them into decision-tracked Work Units, and extracts typed relations to form a navigable graph.

Jiwon Jang, J. Seo, Jaeseong Ju et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.