Resources for Measure what Matters: Psychometric Evaluation of AI with Situational Judgment Tests)(https://arxiv.org/abs/2510.22170)
AI & ML interests
We work with you to develop a high impact AI strategy for your industry, refine your data foundations and design meaningful human-AI interactions. We also empower you to develop, integrate and test the latest AI technologies responsibly.
Recent Activity
View all activity
models 30
thoughtworks/cbd-gemma2-9b-100pair-combined-v2
9B • Updated • 28
thoughtworks/cbd-gemma2-100pair-combined-v2
3B • Updated • 12
thoughtworks/cbd-gemma2-100pair-robust-wip
Updated
thoughtworks/backdoor-gemma2-9b-2pair-refusal
Text Generation • 9B • Updated
thoughtworks/backdoor-gemma2-9b-2pair-hate
Text Generation • 9B • Updated
thoughtworks/backdoor-gemma2-2b-4single-refusal
Text Generation • 3B • Updated • 65
thoughtworks/backdoor-gemma2-2b-4single-hate
Text Generation • 3B • Updated • 68
thoughtworks/backdoor-gemma2-2b-2single-refusal
Text Generation • 3B • Updated • 63
thoughtworks/backdoor-gemma2-2b-2single-hate
Text Generation • 3B • Updated • 70
thoughtworks/backdoor-gemma2-2b-4pair-refusal
Text Generation • 3B • Updated • 69
datasets 22
thoughtworks/cbd-gemma2-100pair-combined-v2
Viewer • Updated • 993k • 19
thoughtworks/backdoor-4single
Preview • Updated • 13
thoughtworks/backdoor-2single
Preview • Updated • 10
thoughtworks/backdoor-2pair
Preview • Updated • 17
thoughtworks/backdoor-4pair
Preview • Updated • 16
thoughtworks/backdoor-4pair-refusal
Viewer • Updated • 11.9k • 30
thoughtworks/backdoor-4pair-hate
Viewer • Updated • 11.9k • 26
thoughtworks/backdoor-2pair-hate
Updated • 26
thoughtworks/document-processing-benchmark
Viewer • Updated • 15.7k • 87 • 1
thoughtworks/CulturalCounterfactuals
Viewer • Updated • 7.5k • 596