Search Results for author:
Found 2 papers, 1 papers with code
Compromising Honesty and Harmlessness in Language Models via Deception Attacks
Recent research on large language models (LLMs) has demonstrated their ability to understand and employ deceptive behavior, even without explicit prompting.
TrainX -- Named Entity Linking with Active Sampling and Bi-Encoders
We demonstrate TrainX, a system for Named Entity Linking for medical experts.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
