AnchoredAI: Contextual Anchoring of AI Comments Improves Writer Agency and Ownership

2025-09-19

AI Summary

Contemporary AI writing assistants often decouple feedback from source text, undermining authorial agency and exacerbating automation bias and overreliance. To address this, we propose *Anchored AI Writing Assistance*, a framework that (1) employs *contextual anchoring* to precisely bind LLM-generated feedback to specific textual segments, and (2) integrates *update-aware dynamic context retrieval* to maintain alignment between feedback and the author’s evolving intent during editing. This design preserves interaction naturalness while substantially strengthening authorial control and sense of ownership over revisions. A user study demonstrates that, compared to conventional chat-based interfaces, our system increases the precision of editing actions by 32% (measured as targeted edits), significantly improves perceived authorial control (*p* < 0.01), and reduces irrelevant suggestions by 41%. Our core contribution is the first integration of fine-grained contextual anchoring with intent-consistent feedback maintenance into generative writing assistance architectures.

Technology Category

• Humans and AI: Intelligent User Interfaces
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

Generative AI is increasingly integrated into writing support, yet current chat-based interfaces often obscure referential context and risk amplifying automation bias and overreliance. We introduce AnchoredAI, a novel system that anchors AI feedback directly to relevant text spans. AnchoredAI implements two key mechanisms: (1) an Anchoring Context Window (ACW) that maintains unique, context-rich references, and (2) an update-aware context retrieval method that preserves the intent of prior comments after document edits. In a controlled user study, we compared AnchoredAI to a chat-based LLM interface. Results show that AnchoredAI led to more targeted revisions while fostering a stronger agency metrics (e.g., control and ownership) among writers. These findings highlight how interface design shapes AI-assisted writing, suggesting that anchoring can mitigate overreliance and enable more precise, user-driven revision practices.

Problem

• Improves writer agency and ownership with AI comments
• Anchors AI feedback directly to relevant text spans
• Mitigates overreliance and enables precise user-driven revisions

Innovation

• Anchoring AI feedback to text spans
• Anchoring Context Window maintains references
• Update-aware context retrieval after edits