“Ultimately, our goal is to develop AI systems whose behaviors can be rigorously understood and predicted, enabling principled control throughout the model lifecycle.”In its own words: pages.cs.wisc.edu
Sharon Li's group at UW-Madison works on the foundations of reliable intelligence: learning systems that know the limits of their competence and make reliable decisions in the open world, currently focusing on reliable LLM and agentic systems.
Show detailsHide details
Received $2M from 3 funders
’23
’24
’25
Led by Sharon Yixuan Li (PI)Checked 26 Oct 2026
Money flows
Where its money came from and where it went. Pick years and what to show; hover a box or ribbon for details, click one to focus it, click the background to see everything.
Funded by
All grants
5 grants totalling $2M, newest first.
2025 4 grants · $1.2M
| Date | Funder | Amount | Purpose |
|---|---|---|---|
| Jul 2025 | Coefficient Giving | $294k | Study on Inductive Biases of LLMs (Sharon Li) source |
| Jul 2025 | Coefficient Giving | $253k | Non-Linear Probes for Feature Discovery & Steering (Sharon Li) source |
| 11 Feb 2025 | Science of Trustworthy AI | ~$370k | Science of Trustworthy AI — AI Safety Science (Feb 2025 cohort): Project: A Conformal Safety Assurance Framework for Large Language Models. One of 27 AI Safety Science awards; per-project amount undisclosed. — Science of Trustworthy AI — AI Safety Science (Feb 2025 cohort) source |
| 2025 | Science of Trustworthy AI | ~$250k | Science of Trustworthy AI — Inference-Time Compute (2025 cohort): Project: Reasoning with Foresight: Safe Inference via Q-Value Guided Decoding. Inference-time compute safety cohort; per-project amount undisclosed (RFP cap $500K). Note: second Schmidt Sciences trustworthy-AI awar source |
2023 1 grant · $793k
| Date | Funder | Amount | Purpose |
|---|---|---|---|
| Sep 2023 | NSF Safe Learning-Enabled Systems | $793k | NSF SLES award 2331669: Foundations of Safety-Aware Learning in the Wild. Estimated total award; 2023 cohort (NSF 23-562, $10.9M announced 31 Oct 2023); programme run with Open Philanthropy and Good Ventures source |