Picture for Sam Bowman

Sam Bowman

Future Events as Backdoor Triggers: Investigating Temporal Vulnerabilities in LLMs

Add code
Jul 04, 2024
Viaarxiv icon

Language Models (Mostly) Know What They Know

Add code
Jul 16, 2022
Figure 1 for Language Models (Mostly) Know What They Know
Figure 2 for Language Models (Mostly) Know What They Know
Figure 3 for Language Models (Mostly) Know What They Know
Figure 4 for Language Models (Mostly) Know What They Know
Viaarxiv icon

Can Unconditional Language Models Recover Arbitrary Sentences?

Add code
Jul 10, 2019
Figure 1 for Can Unconditional Language Models Recover Arbitrary Sentences?
Figure 2 for Can Unconditional Language Models Recover Arbitrary Sentences?
Figure 3 for Can Unconditional Language Models Recover Arbitrary Sentences?
Figure 4 for Can Unconditional Language Models Recover Arbitrary Sentences?
Viaarxiv icon

Detecting and Explaining Crisis

Add code
May 26, 2017
Figure 1 for Detecting and Explaining Crisis
Figure 2 for Detecting and Explaining Crisis
Figure 3 for Detecting and Explaining Crisis
Figure 4 for Detecting and Explaining Crisis
Viaarxiv icon