research
∙
07/05/2023
Jailbroken: How Does LLM Safety Training Fail?
Large language models trained for safety and harmlessness remain suscept...
share
research
∙
03/14/2023
Eliciting Latent Predictions from Transformers with the Tuned Lens
We analyze transformers from the perspective of iterative inference, see...
research
∙
02/24/2022
Capturing Failures of Large Language Models via Human Cognitive Biases
Large language models generate complex, open-ended outputs: instead of o...
research
∙
03/05/2021
Measuring Mathematical Problem Solving With the MATH Dataset
Many intellectual endeavors require mathematical problem solving, but th...
research
∙
06/29/2020
The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization
We introduce three new robustness benchmarks consisting of naturally occ...
research
∙
11/02/2018
Stronger Data Poisoning Attacks Break Data Sanitization Defenses
Machine learning models trained on data from the outside world can be co...
research
∙
06/21/2016
