JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models
Paper
•
2404.01318
•
Published
Edgar Dobriban
ed13
·
AI & ML interests
None yet
Recent Activity
authored
a paper
15 days ago
JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large
Language Models
authored
a paper
15 days ago
Demystifying Disagreement-on-the-Line in High Dimensions
authored
a paper
15 days ago
PAC Prediction Sets Under Label Shift
Organizations
None yet
authored
12
papers
15 days ago
Demystifying Disagreement-on-the-Line in High Dimensions
Paper
•
2301.13371
•
Published
PAC Prediction Sets Under Label Shift
Paper
•
2310.12964
•
Published
Statistical Methods in Generative AI
Paper
•
2509.07054
•
Published
•
11
Conformal Information Pursuit for Interactively Guiding Large Language Models
Paper
•
2507.03279
•
Published
Foundations of Top-$k$ Decoding For Language Models
Paper
•
2505.19371
•
Published
Synthetic-Powered Predictive Inference
Paper
•
2505.13432
•
Published
Batch Predictive Inference
Paper
•
2409.13990
•
Published
A Confidence Interval for the $\ell_2$ Expected Calibration Error
Paper
•
2408.08998
•
Published
Evaluating the Performance of Large Language Models via Debates
Paper
•
2406.11044
•
Published
One-Shot Safety Alignment for Large Language Models via Optimal Dualization
Paper
•
2405.19544
•
Published
Jailbreaking Black Box Large Language Models in Twenty Queries
Paper
•
2310.08419
•
Published