Samuel Simko

According to our database, Samuel Simko authored at least 3 papers between 2025 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering.

Saad Hossain, Tom Tseng, Punya Syon Pandey, Samanvay Vajpayee, Matthew Kowal, Nayeema Nonta, Samuel Simko, Stephen Casper, Zhijing Jin, Kellin Pelrine, Sirisha Rambhatla

CoRR, February, 2026

2025

Accidental Misalignment: Fine-Tuning Language Models Induces Unexpected Vulnerability.

Punya Syon Pandey, Samuel Simko, Kellin Pelrine, Zhijing Jin

CoRR, May, 2025

Improving Large Language Model Safety with Contrastive Representation Learning.

Samuel Simko, Mrinmaya Sachan, Bernhard Schölkopf, Zhijing Jin

Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025