Ercin Dedeoglu PRO

Ercin

·

https://ercin.info

AI & ML interests

AI Architect. Sovereign LLM, RAG and agentic AI for regulated banking. LLM red teaming before go-live: open scorer + checklist. ercin.info

Recent Activity

updated a Space about 12 hours ago

Ercin/llm-red-teaming-banking-severity-scorer

commentedon a paper about 14 hours ago

Identically Trained Language Models Break on Different Jailbreaks

commentedon a paper 1 day ago

Policy Is Not Capability: Some Safety Benchmarks Measure Which Definition of "Unsafe" You Trained On

View all activity

Organizations

commented a paper about 14 hours ago

Identically Trained Language Models Break on Different Jailbreaks

Paper • 2610.34074 • Published 5 days ago •

commented a paper 1 day ago

Policy Is Not Capability: Some Safety Benchmarks Measure Which Definition of "Unsafe" You Trained On

Paper • 2610.25060 • Published 12 days ago • 18 •

commented 2 papers 3 days ago

Policy Is Not Capability: Some Safety Benchmarks Measure Which Definition of "Unsafe" You Trained On

Paper • 2610.25060 • Published 12 days ago • 18 •

FinRED: An Expert-Guided Benchmark Generation and Evaluation Framework for Financial LLM Red-Teaming

Paper • 2606.19887 • Published 18 days ago •

commented a paper 4 days ago

Risk-Adjusted Harm Scoring for Automated Red Teaming for LLMs in Financial Services

Paper • 2603.10807 • Published Aug 31 •

commented a paper 5 days ago

Policy Is Not Capability: Some Safety Benchmarks Measure Which Definition of "Unsafe" You Trained On

Paper • 2610.25060 • Published 12 days ago • 18 •