Matt Wu | Search arXiv

arXiv2026

Automated Feedback to Peer Tutors Increases Their Talk Moves and Learner Reasoning but Not the Balance of Talk

Automated feedback on classroom discourse improves instruction in professional and online teaching contexts, and recent work suggests that delivering similar feedback to learners may strengthen these effects by sharing responsibility for participation. Whether this holds in small-group volunteer tutoring has not been tested. We present results from a randomized controlled trial across two four-week SAT mathematics bootcamps on the Schoolhouse.world platform, involving 1,030 volunteer tutors, 7,443 learners and 6,508 recorded sessions. Tutors were randomly assigned to receive no feedback, automated feedback on their own discourse, or that feedback together with participation feedback delivered to their learners under one of two motivational framings. Feedback to tutors increased eliciting of learner ideas, uptake of learner contributions, and learner reasoning by 8-15%, and the pattern replicated across both bootcamps. However, tutor talk time, which averaged 91.5% in the control group, did not change in any condition, and learner-facing feedback did not further change discourse. Interviews with 17 tutors indicate that they adopted the moves the feedback recommended but were limited by learners who did not respond. Interviews with 13 learners suggest why the learner-facing feedback had little effect: it reported a group-level rather than a learner-level statistic, some learners preferred to listen, and learner-to-learner interaction was rare in these sessions. Automated feedback can change how tutors invite learner thinking, but shifting how much learners talk likely requires changes beyond feedback.

cs.CL↗

arXiv2024

Transforming Redaction: How AI is Revolutionizing Data Protection

Document redaction is a crucial process in various sectors to safeguard sensitive information from unauthorized access and disclosure. Traditional manual redaction methods, such as those performed using Adobe Acrobat, are labor-intensive, error-prone, and time-consuming. With the burgeoning volume of digital documents, the demand for more efficient and accurate redaction techniques is intensifying. This study presents the findings from a controlled experiment that compares traditional manual redaction, a redaction tool powered by classical machine learning algorithm, and AI-assisted redaction tools (iDox.ai Redact). The results indicate that iDox.ai Redact significantly outperforms manual methods, achieving higher accuracy and faster completion times. Conversely, the competitor product, classical machine learning algorithm and with necessitates manual intervention for certain sensitive data types, did not exhibit a statistically significant improvement over manual redaction. These findings suggest that while advanced AI technologies like iDox.ai Redact can substantially enhance data protection practices by reducing human error and improving compliance with data protection regulations, there remains room for improvement in AI tools that do not fully automate the redaction process. Future research should aim to enhance AI capabilities and explore their applicability across various document types and professional settings.

cs.CY↗