NoTeeline: Supporting Real-Time, Personalized Notetaking with LLM-Enhanced Micronotes

TL;DR

The results suggest that NoTeeline enables users to integrate LLM assistance in a familiar notetaking workflow while ensuring consistency with their preferences—providing an example of how to address broader challenges in designing AI-assisted tools to augment human capabilities without compromising user autonomy and personalization.

Abstract

Taking notes quickly while effectively capturing key information can be challenging, especially when watching videos that present simultaneous visual and auditory streams. Manually taken notes often miss crucial details due to the fast-paced nature of the content, while automatically generated notes fail to incorporate user preferences and discourage active engagement with the content. To address this, we propose an interactive system, NoTeeline, for supporting real-time, personalized notetaking. Given micronotes, NoTeeline automatically expands them into full-fledged notes using a Large Language Model (LLM). The generated notes build on the content of micronotes by adding relevant details while maintaining consistency with the user's writing style. In a within-subjects study (n=12), we found that NoTeeline creates high-quality notes that capture the essence of participant micronotes with 93.2% factual correctness and accurately align with participant writing style (8.33% improvement). Using NoTeeline, participants could capture their desired notes with significantly reduced mental effort, writing 47.0% less text and completing their notes in 43.9% less time compared to a manual notetaking baseline. Our results suggest that NoTeeline enables users to integrate LLM assistance in a familiar notetaking workflow while ensuring consistency with their preferences - providing an example of how to address broader challenges in designing AI-assisted tools to augment human capabilities without compromising user autonomy and personalization.

Figures (14)

• Figure 1: The NoTeeline user interface consists of (a) the Cues panel (outlined in blue) for review questions generated based on the notes, (b) the Notes panel (outlined in orange) for user notetaking and note expansion, and (c) the Summary panel (outlined in purple) for note summary. The layout is inspired by the Cornell method, as seen in the side-by-side comparison. The onboarding session, highlighted on the left, collects example notes from the user.
• Figure 2: Micronote expansion. Users can toggle between the micronote and the expanded note by clicking the Expand/Reduce buttons.
• Figure 3: Note organization by themes (some texts have been cropped for clarity). Users can organize the notes by themes or toggle back to the original serial in which they took the notes.
• Figure 4: Distribution of pause and skips used by each participant in NoTeeline (left) and Baseline (right). In NoTeeline, the count of pause and skip is significantly less than the baseline. An empty bar depicts that the user did not pause or skip at all.
• Figure 5: Comparison of (a) note length, (b) writing time and (c) count for each participant between NoTeeline and baseline. The majority of the users took the higher amount of notes in NoTeeline in less time.