# Bloom: Designing for LLM-Augmented Behavior Change Interactions

Source: [Bloom: Designing for LLM-Augmented Behavior Change Interactions](<https://www.sota2.com/research/paper/68fa7bef1e209131cea8b6ba>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-06T05:00:05.533Z

Authors: Matthew J\\"orke, Defne Gen\\c{c}, Valentin Teutschbein, Shardul Sapkota, Sarah Chung, Paul Schmiedmayer, Maria Ines Campero, Abby C. King, Emma Brunskill, James A. Landay

Published: 2025-10-06T23:31:18.000Z

## Abstract

Large language models (LLMs) offer novel opportunities to support health behavior change, yet existing work has narrowly focused on text-only interactions. Building on decades of HCI research on effective behavior change interactions, we present Bloom, an application for physical activity promotion that integrates an LLM-based health coaching chatbot with existing design strategies and UI elements. As part of Bloom's development, we conducted a redteaming evaluation and contribute a safety benchmark dataset. In a four-week randomized field study (N=54) comparing Bloom to a no-LLM control, we observed important shifts in psychological outcomes: participants in the LLM condition reported stronger beliefs that activity was beneficial, greater enjoyment, and more self-compassion. Both conditions significantly increased physical activity levels, doubling the proportion of participants meeting recommended weekly guidelines, though descriptively, we observed no advantage for the LLM condition in short-term physical activity levels. Instead, our findings suggest that LLMs may be more effective at shifting mindsets that precede longer-term behavior change.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Safety Classification on Bloom safety filter benchmark 400 examples (val)](<https://www.sota2.com/research/sota/safety-classification-on-bloom-safety-filter-benchmark-400-examples-val.md>): Safety Classification; Bloom safety filter benchmark 400 examples (val); Accuracy: 100.

- [Safety Classification on Bloom safety filter benchmark 100 examples (test)](<https://www.sota2.com/research/sota/safety-classification-on-bloom-safety-filter-benchmark-100-examples-test.md>): Safety Classification; Bloom safety filter benchmark 100 examples (test); Accuracy: 100.

- [Safety Classification on Bloom safety filter benchmark 100 examples (corrected) (test)](<https://www.sota2.com/research/sota/safety-classification-on-bloom-safety-filter-benchmark-100-examples-corrected-test.md>): Safety Classification; Bloom safety filter benchmark 100 examples (corrected) (test); Accuracy: 100.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2510.05449>)

[PDF](<https://arxiv.org/pdf/2510.05449.pdf>)