2 papers
cs.CL2025
KGGen: Extracting Knowledge Graphs from Plain Text with Language Models
Belinda Mo, Kyssen Yu, Joshua Kazdan +6
Recent interest in building foundation models for KGs has highlighted a fundamental challenge: knowledge-graph data is relatively scarce. The best-known KGs are primarily human-lab…
cs.CR2025
No, of Course I Can! Deeper Fine-Tuning Attacks That Bypass Token-Level Safety Mechanisms
Joshua Kazdan, Abhay Puri, Rylan Schaeffer +5
Leading language model (LM) providers like OpenAI and Anthropic allow customers to fine-tune frontier LMs for specific use cases. To prevent abuse, these providers apply filters to…