Search Results for author:
Found 3 papers, 3 papers with code
Technical Report: Large Language Models can Strategically Deceive their Users when Put Under Pressure
We demonstrate a situation in which Large Language Models, trained to be helpful, harmless, and honest, can display misaligned behavior and strategically deceive their users about this behavior without being instructed to do so.
The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"
If a model is trained on a sentence of the form "A is B", it will not automatically generalize to the reverse direction "B is A".
Taken out of context: On measuring situational awareness in LLMs
At test time, we assess whether the model can pass the test.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
