The misuse of large language models (LLMs) has drawn significant attention from the general public and LLM vendors. One particular type of adversarial prompt, known as jailbreak prompt, has...

The recent wave of generative AI has sparked unprecedented global attention, with both excitement and concern over potentially superhuman levels of artificial intelligence: models now take only...

200Bn Weights of Responsibility The Stress of Working in Modern AI Felix Hill, Oct 2024 The field of AI has changed irrevocably in the last 2 years. ChatGPT is approaching 200m monthly users. Gemini...

Summary

Data imbalance in training data often leads to biased predictions from trained models, which in turn causes ethical and social issues. A straightforward solution is to carefully curate training...