Probably Approximately a Scientific Blog

JANUARY 12, 2021

Figure 1: adversarial examples in computer vision (left) and natural language processing tasks (right). Machine learning models today perform reasonably well on perception tasks (image and speech recognition). As we've seen earlier, commonsense knowledge is immeasurably vast, so much of it is not documented.

Natural Language Processing 52

Natural Language Processing BERT NLP Neural Network 52

Pickl AI

DECEMBER 5, 2024

Retrieval Augmented Generation (RAG) is a cutting-edge approach in natural language processing that combines two powerful techniques: information retrieval and text generation. The core idea is to enhance a language model’s output by grounding it in external, up-to-date, or domain-specific information.

Natural Language Processing 52

Natural Language Processing Conversational AI Chatbots Artificial Intelligence 52

AWS Machine Learning Blog

JULY 9, 2024

Quantitative reasoning This task determines if, given a question and lengthy documents, the model can perform complex calculations and correctly reason to produce an accurate answer. The questions are written by financial professionals using real-world data and financial knowledge. As pointed out in Anthropic’s Claude 3.5

Generative AI 132

Generative AI LLM Machine Learning AI 132