Vivek Hebbar

According to our database, Vivek Hebbar authored at least 5 papers between 2024 and 2026.

Collaborative distances:

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

2026

Removing Sandbagging in LLMs by Training with Weak Supervision.

Emil Ryd, Henning Bartsch, Julian Stastny, Joe Benton, Vivek Hebbar

CoRR, April, 2026

Auditing Sabotage Bench: A Benchmark for Detecting and Fixing Research Sabotage in ML Codebases.

Eric Gan, Aryan Bhatt, Buck Shlegeris, Julian Stastny, Vivek Hebbar

CoRR, April, 2026

2025

Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs.

Abhay Sheshadri, Aidan Ewart, Phillip Guo, Aengus Lynch, Cindy Wu, Vivek Hebbar, Henry Sleight, Asa Cooper Stickland, Ethan Perez, Dylan Hadfield-Menell, Stephen Casper

Trans. Mach. Learn. Res., 2025

Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats.

Jiaxin Wen, Vivek Hebbar, Caleb Larson, Aryan Bhatt, Ansh Radhakrishnan, Mrinank Sharma, Henry Sleight, Shi Feng, He He, Ethan Perez, Buck Shlegeris, Akbir Khan

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024

Targeted Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs.

Abhay Sheshadri, Aidan Ewart, Phillip Guo, Aengus Lynch, Cindy Wu, Vivek Hebbar, Henry Sleight, Asa Cooper Stickland, Ethan Perez, Dylan Hadfield-Menell, Stephen Casper

CoRR, 2024