arXiv:2608. 12582v1 Announce Type: cross Abstract: AI journaling tools can tailor prompts to a person's own sensed behavior, but it is unclear which behaviors respond to them.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
arXiv:2608.21841v1 Announce Type: new Abstract: Conversational AI increasingly shapes consequential decisions, yet users have limited support for recognizing and resisting manipulation. We present AI...
arXiv:2609.01257v1 Announce Type: new Abstract: As LLM-based human simulators are increasingly used for policy, evaluation, and training, they must faithfully reproduce real behavioral patterns. Whil...
arXiv:2603. 23433v3 Announce Type: replace Abstract: AI agents are becoming active decision-makers on the Internet.
The paper introduces ASURRE, a benchmark dataset for detecting AI‑assisted responses in online surveys. It evaluates how different LLM usage strategies—ranging from full generation to persona‑grounded agentic completion—affect the performance of existing machine‑generated text detectors. The study finds that while naive AI usage is easily detected, more sophisticated persona‑grounded agents approach chance performance, yet still leave identifiable behavioural traces that can be aggregated to improve detection.
The study examines pseudo‑label augmentation for affect sensing in small collaborative groups using the GroupAffect‑4 dataset, which includes wearable physiology, eye tracking, personality traits, and post‑task valence, arousal, and dominance (VAD) labels. Various augmentation strategies—no augmentation, Gaussian Process pseudo‑labelling, personality‑aware trust weighting, and joint personality‑plus‑confidence weighting—were evaluated within a shared target‑construction pipeline. Results show that pseudo‑label augmentation improves performance over a labelled‑only baseline in the known‑team setting, with the joint personality‑plus‑confidence variant achieving the highest dominance score, while personality similarity mainly serves as a same‑team filter rather than a calibrated trust signal.
arXiv:2604. 03881v2 Announce Type: replace-cross Abstract: Encouraging pro-environmental behavior remains a major challenge for sustainable cities.