Precise In-Parameter Concept Erasure in Large Language Models
Paper • 2505.22586 • Published • 1
Yoav Gur-Arieh
yoavgurarieh
AI & ML interests
None yet
Recent Activity
upvoted a paper about 12 hours ago
Faithfulness Metrics Don't Measure Faithfulness: A Meta-Evaluation with Ground Truth authored a paper about 15 hours ago
Precise In-Parameter Concept Erasure in Large Language Models authored a paper about 15 hours ago
Enhancing Automated Interpretability with Output-Centric Feature DescriptionsOrganizations
None yet
authored 4
papers about 15 hours ago
Enhancing Automated Interpretability with Output-Centric Feature Descriptions
Paper • 2501.08319 • Published • 11
LMEnt: A Suite for Analyzing Knowledge in Language Models from Pretraining Data to Representations
Paper • 2509.03405 • Published • 24
Mixing Mechanisms: How Language Models Retrieve Bound Entities In-Context
Paper • 2510.06182 • Published • 9
authored a
paper about 24 hours ago
authored a
paper 1 day ago
authored a
paper 12 months ago
authored a
paper over 1 year ago