Writing involves diverse cognitive activities, from ideation to revision, and writers' needs vary across individuals and moments. Proactive AI promises to provide the right support at the right time,...
arXiv:2609.01588v1 Announce Type: cross Abstract: Writing involves diverse cognitive activities, from ideation to revision, and writers' needs vary across individuals and moments. Proactive AI promis...
CoWriter is a proactive agentic system that adapts expert human co‑authoring methodologies from cognitive science to guide the entire writing workflow and actively encourage user engagement. In an exploratory user study, authors using CoWriter expressed their perspectives more clearly, felt greater ownership of the document, and engaged with the agent 2.2× more often than a standard LLM baseline. External reader judges also rated CoWriter‑generated texts higher in human‑touch qualities such as storytelling and personal experience integration.
arXiv:2610.34770v1 Announce Type: cross Abstract: Direct messaging is often employed by social media content creators to directly interact with followers. Those creators attempt to engage with follow...
The study examines how teens interact with companion AI chatbots, revealing that these systems offer comfort, recognition, identity exploration, and relationship rehearsal. However, teens also experience problematic attachment, social substitution, emotional dependence, and disruptions to academic and social life. The findings highlight the need for safety measures that address long‑term relationships, user‑controlled memory, privacy, relational boundaries, and healthy disengagement.
Communities often respond to potentially AI-assisted work by asking three questions: Was AI used? Was that use disclosed? Can hidden use be detected? These questions place AI use itself at the center...
The paper introduces CounselReflect, a tool that converts counseling quality metrics into a framework for users to reflect on their mental‑health AI conversations. Through interviews with 21 users, the study finds that while most participants rarely reflect on their interactions, they identify specific questions they would like such a tool to address. The findings also reveal that users tend to confirm existing beliefs and focus on familiar dimensions, highlighting the need for reflection tools to expose blind spots and encourage a more comprehensive examination of AI interactions, especially when revisiting emotionally charged exchanges.
arXiv:2605.30273v2 Announce Type: replace-cross Abstract: Large language models (LLMs) show promise in generating supportive responses for mental health queries, but improving their usefulness, empat...
The paper surveys 61 studies on mental‑health AI and identifies a misalignment in how trust is evaluated across disciplines. It proposes a three‑layer framework—human‑oriented, interaction‑oriented, and AI‑oriented trust—and maps stakeholder perspectives onto these layers. The authors argue that future research should focus on calibrating human trust to actual interaction and AI trustworthiness rather than merely maximizing perceived trust.
The paper examines how AI involvement in human collaboration can lead to unowned judgment, where decisions shaped by AI lack a clear accountable human or institution. Through cases of AI-assisted peer review and concealed AI use in creative work, it shows that contribution dissolution weakens responsibility and that fear of losing credit can deter disclosure. The authors argue for clearer distinctions of AI roles, identification of judgments needing human ownership, and conditions that allow disclosure without penalty, aiming to make AI-shaped contributions discussable, creditable, contestable, and repairable.
arXiv:2609.15696v1 Announce Type: cross Abstract: Generative AI (GenAI) tools are increasingly woven into how blind and low-vision (BLV) people communicate, not only with digital information, but wit...
The article describes the design, operation, and impact of the Community-Driven API and AI Writer for Openly Scaling Community Notes on X. It explains how the AI Note Writer API, launched in September 2025, allows AI to propose notes while users retain control over which notes are shown, and highlights that the Community Writer—an open‑source client—generates 52% of notes deemed helpful and is faster than other writers. The study shows AI notes complement human contributions, covering 42% of posts with helpful notes that have no human alternative, and 30% of posts with only human notes, indicating a synergistic relationship. "whyItMatters":"The work demonstrates how an open, community‑driven AI API can scale content moderation and enrichment on a social platform while preserving user control and complementing human effort."