Crisis Text Line fine-tunes an LLM-powered conversation simulator on Databricks to train crisis counselors
Crisis Text Line, a nonprofit text-based mental health crisis service supporting 1.3 million conversations a year, used Databricks MLflow and fine-tuned versions of Llama 2, trained on synthetic conversation role-plays created by clinical staff, to build an LLM-powered conversation simulator that lets new volunteer crisis counselors practice engagement strategies without real-world repercussions. The simulator has been used by over 50 volunteers and clinicians, and the organization is also developing a conversation-phase classifier to help assess response quality.
Overview
Crisis Text Line, a nonprofit text-based mental health crisis service supporting 1.3 million conversations a year, used Databricks MLflow and fine-tuned versions of Llama 2, trained on synthetic conversation role-plays created by clinical staff, to build an LLM-powered conversation simulator that lets new volunteer crisis counselors practice engagement strategies without real-world repercussions. The simulator has been used by over 50 volunteers and clinicians, and the organization is also developing a conversation-phase classifier to help assess response quality.
This entry has 13 published fields tied to exact passages in an immutable source capture.
Inspect the highlighted sourceThe challenge
Crisis Text Line's data landscape was siloed in terms of record reporting, with business rules and context inconsistent or lost in data silos, causing downstream operational teams to struggle making efficient, real-time decisions; legacy systems also suffered simple queries timing out and multiple points of failure from batch-script data transformation.
The solution
Crisis Text Line centralized its data on the Databricks Data + AI Platform to create a single source of truth with a federated data store, used Unity Catalog for granular table- and column-level access control, MLflow to manage the full model lifecycle, and Spark Declarative Pipelines for its post-processing pipeline, then fine-tuned versions of Llama 2 on synthetic conversation role-plays from clinical staff to build an LLM-powered conversation simulator.
Reported business value
Databricks helped Crisis Text Line dramatically reduce the time required to make critical datasets available to clinical teams, analytics groups and future ML work, increased user adoption of dashboard artifacts, increased program ROI as customers and affiliates learned to trust its operational and analytical expertise, and reduced infrastructure and engineering overhead; the LLM-powered conversation simulator has been used by over 50 real volunteers and clinicians to boost training confidence.
Sources
Open any source and check the claim yourself — that is the point of the register.
This record was researched and written with AI assistance, and its claims were checked against the sources above. (EU AI Act art. 50 transparency notice.)
Other technology & software entries in the register.
HP crafts marketing campaigns that resonate with customers using Databricks and Uniphore
HP centralized first-party customer data on the Databricks Data + AI Platform with Delta Lake and Unity Catalog, and connected it to Uniphore's HybridCompute for federated query pushdown, cutting campaign setup from 2 weeks to 2 hours and processing 400 million records in seconds.
Building a safer and more sustainable world
Novade, a construction management software company, partnered with Databricks to modernize its analytics and ML infrastructure, moving from a homegrown Apache Airflow stack to the Databricks Data + AI Platform with Delta Lake, Unity Catalog and MLflow. The move reduced total cost of ownership by 60% and supported a 100% increase in new clients, while enabling ML models for predicting incident risk affecting worker safety and project delivery schedules.
SafeGraph optimizes geospatial data processing with Databricks and Delta Sharing
SafeGraph used the Databricks Data + AI Platform, Delta Lake, Delta Sharing and MLflow to process petabytes of geospatial data and feed predictive models, achieving 2x-10x faster spatial querying, indexing and partitioning and a 50% reduction in peak memory consumption compared to other platforms, while reducing data access time for partners from months to minutes via Delta Sharing.
Transforming Weather Forecasting with Lakeflow Jobs
AccuWeather migrated from on-premises infrastructure to Databricks and Lakeflow Jobs, working with Datadog for observability, to unify diverse weather data formats and orchestrate 4,500+ weekly jobs. Lakeflow Jobs coordinates the ingestion of multiple weather models, triggers machine learning processes that weight and blend different forecasts, and manages complex job dependencies for reinforcement training workflows used in AccuWeather's proprietary forecasting engine. AccuWeather reports 3x faster dataset development (three months to one month per dataset), a 50% reduction in unactionable alerts, and 50% cost savings on serverless job usage.
AccuWeatherLakeflow Jobs · Delta Sharing · DatadogWas this helpful?
Your feedback helps us improve our use case database