Hugging Face's logo
Activity Feed

AI & ML interests

AI Safety & Reliability, Responsible Computing, and Efficient ML

Recent Activity
Czardas  submitted a paper about 4 hours ago
Whom to Query for What: Adaptive Group Elicitation via Multi-Turn LLM Interactions
Czardas  submitted a paper about 5 hours ago
Rubrics as an Attack Surface: Stealthy Preference Drift in LLM Judges
pyfccc  updated a dataset 1 day ago
ZDCSlab/ripd-dataset
View all activity

Papers

Whom to Query for What: Adaptive Group Elicitation via Multi-Turn LLM Interactions

Rubrics as an Attack Surface: Stealthy Preference Drift in LLM Judges

View all Papers

Organization Card
Community About org cards

ZD Lab @ UNC–Chapel Hill

Our research areas include:

  • AI Safety & Reliability — risk control, uncertainty quantification, ML security
  • Responsible Computing — societal impacts and human–AI interaction
  • Efficient ML — efficient reasoning and test-time scaling

Collections 1

Rubrics as an Attack Surface (RIPD)
This collection releases the official artifacts accompanying “Rubrics as an Attack Surface: Stealthy Preference Drift in LLM Judges.”
Rubrics as an Attack Surface (RIPD)
This collection releases the official artifacts accompanying “Rubrics as an Attack Surface: Stealthy Preference Drift in LLM Judges.”