# CatAlyst: Domain-Extensible Intervention for Preventing Task Procrastination Using Large Generative Models

arXiv: https://arxiv.org/abs/2302.05678 · HTML: https://mlsanity.com/paper/2302.05678/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 90 references that are in the map.
- First posted on arXiv 11 Feb 2023.

## Builds on (most cited first, 26 of 26)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Model Cards for Model Reporting](https://mlsanity.com/paper/1810.03993/) (2018)
- [Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm](https://mlsanity.com/paper/2102.07350/) (2021)
- [The Woman Worked as a Babysitter: On Biases in Language Generation](https://mlsanity.com/paper/1909.01326/) (2019)
- [CoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model Capabilities](https://mlsanity.com/paper/2201.06796/) (2022)
- [Sentence Encoders on STILTs: Supplementary Training on Intermediate Labeled-data Tasks](https://mlsanity.com/paper/1811.01088/) (2018)
- [Carbontracker: Tracking and Predicting the Carbon Footprint of Training Deep Learning Models](https://mlsanity.com/paper/2007.03051/) (2020)
- [Gmail Smart Compose: Real-Time Assisted Writing](https://mlsanity.com/paper/1906.00080/) (2019)
- [Productivity Assessment of Neural Code Completion](https://mlsanity.com/paper/2205.06537/) (2022)
- [PEER: A Collaborative Language Model](https://mlsanity.com/paper/2208.11663/) (2022)
- [Unremarkable AI: Fitting Intelligent Decision Support into Critical, Clinical Decision-Making Processes](https://mlsanity.com/paper/1904.09612/) (2019)
- [Beyond Text Generation: Supporting Writers with Continuous Automatic Text Summaries](https://mlsanity.com/paper/2208.09323/) (2022)
- [Ask Not What AI Can Do, But What AI Should Do: Towards a Framework of Task Delegability](https://mlsanity.com/paper/1902.03245/) (2019)
- [Telling Stories from Computational Notebooks: AI-Assisted Presentation Slides Creation for Presenting Data Science Work](https://mlsanity.com/paper/2203.11085/) (2022)
- [Nudge: Accelerating Overdue Pull Requests Towards Completion](https://mlsanity.com/paper/2011.12468/) (2020)
- [Examining Autocompletion as a Basic Concept for Interaction with Generative AI](https://mlsanity.com/paper/2201.06892/) (2022)
- [Mindless Attractor: A False-Positive Resistant Intervention for Drawing Attention Using Auditory Perturbation](https://mlsanity.com/paper/2101.08621/) (2021)
- [AI for human assessment: What do professional assessors need?](https://mlsanity.com/paper/2204.08471/) (2022)
- [How can Email Interventions Increase Students' Completion of Online Homework? A Case Study Using A/B Comparisons](https://mlsanity.com/paper/2208.05087/) (2022)
- [Writers Gonna Wait: The Effectiveness of Notifications to Initiate Aversive Action in Writing Procrastination](https://mlsanity.com/paper/2101.10191/) (2021)

## Built on by (most cited first, 10 of 10)

- [MindfulDiary: Harnessing Large Language Model to Support Psychiatric Patients' Journaling](https://mlsanity.com/paper/2310.05231/) (2023)
- [Classroom Simulacra: Building Contextual Student Generative Agents in Online Education for Learning Behavioral Simulation](https://mlsanity.com/paper/2502.02780/) (2025)
- [Co-Writing with AI, on Human Terms: Aligning Research with User Demands Across the Writing Process](https://mlsanity.com/paper/2504.12488/) (2025)
- [Collage is the New Writing: Exploring the Fragmentation of Text and User Interfaces in AI Tools](https://mlsanity.com/paper/2405.17217/) (2024)
- [Understanding Communication Preferences of Information Workers in Engagement with Text-Based Conversational Agents](https://mlsanity.com/paper/2410.20468/) (2024)
- [Survey of User Interface Design and Interaction Techniques in Generative AI Applications](https://mlsanity.com/paper/2410.22370/) (2024)
- [AI Rivalry as a Craft: How Resisting and Embracing Generative AI Reshape Writing Professions](https://mlsanity.com/paper/2503.09901/) (2025)
- [The Consensus Trap: Dissecting Subjectivity and the "Ground Truth" Illusion in Data Annotation](https://mlsanity.com/paper/2602.11318/) (2026)
- ["With Great Power Comes Great Responsibility!": Student and Instructor Perspectives on the influence of LLMs on Undergraduate Engineering Education](https://mlsanity.com/paper/2309.10694/) (2023)
- [Adaptive Human-Agent Teaming: A Review of Empirical Studies from the Process Dynamics Perspective](https://mlsanity.com/paper/2504.10918/) (2025)

## Abstract (arXiv)

CatAlyst uses generative models to help workers' progress by influencing their task engagement instead of directly contributing to their task outputs. It prompts distracted workers to resume their tasks by generating a continuation of their work and presenting it as an intervention that is more context-aware than conventional (predetermined) feedback. The prompt can function by drawing their interest and lowering the hurdle for resumption even when the generated continuation is insufficient to substitute their work, while recent human-AI collaboration research aiming at work substitution depends on a stable high accuracy. This frees CatAlyst from domain-specific model-tuning and makes it applicable to various tasks. Our studies involving writing and slide-editing tasks demonstrated CatAlyst's effectiveness in helping workers swiftly resume tasks with a lowered cognitive load. The results suggest a new form of human-AI collaboration where large generative models publicly available but imperfect for each individual domain can contribute to workers' digital well-being.