Research

AI21’s AI Code of Conduct

Jamba-1.5: Hybrid Transformer-Mamba Models at Scale

Jamba: A Hybrid Transformer-Mamba Language Model

Generating Benchmarks for Factuality Evaluation of Language Models

Parallel Context Windows for Large Language Models

Human or Not? A Gamified Approach to the Turing Test

AI21 Summarise API: Technial Evaluation

In-Context Retrieval-Augmented Language Models

Best practices for deploying language models

MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning

Standing on the Shoulders of Giant Frozen Language Models

Jurassic-1: Technical Details & Evaluation

Exemplar Guided Active Learning

PMI-Masking: Principled masking of correlated spans

The Cost of Training NLP Models: A Concise Overview

SenseBERT: Driving Some Sense into BERT

Auxiliary Tuning and its Application to Conditional Text Generation