AnchoredAI: Contextual Anchoring of AI Comments Improves Writer Agency and Ownership
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911163694972928 |
|---|---|
| author | Lou, Martin Crowley, Jackie Dodson, Samuel Yoon, Dongwook |
| author_facet | Lou, Martin Crowley, Jackie Dodson, Samuel Yoon, Dongwook |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_16128 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AnchoredAI: Contextual Anchoring of AI Comments Improves Writer Agency and Ownership Lou, Martin Crowley, Jackie Dodson, Samuel Yoon, Dongwook Human-Computer Interaction 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. |
| title | AnchoredAI: Contextual Anchoring of AI Comments Improves Writer Agency and Ownership |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2509.16128 |