Risultati della ricerca - Simko, Samuel

Improving Large Language Model Safety with Contrastive Representation Learning di Simko, Samuel, Sachan, Mrinmaya, Schölkopf, Bernhard, Jin, Zhijing

Testo

Accidental Vulnerability: Factors in Fine-Tuning that Shift Model Safeguards di Pandey, Punya Syon, Simko, Samuel, Pelrine, Kellin, Jin, Zhijing

Testo

TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering di Hossain, Saad, Tseng, Tom, Pandey, Punya Syon, Vajpayee, Samanvay, Kowal, Matthew, Nonta, Nayeema, Simko, Samuel, Casper, Stephen, Jin, Zhijing, Pelrine, Kellin, Rambhatla, Sirisha

Testo