Skip to Main Menu
Skip to Main Content
Skip to Footer

Research hero gradient

Research hero gradient

Research

Our team works at the frontier of AI progress to solve complex scientific challenges that can help deliver real-world business solutions.

Jamba 1.5a: Enhancing AI Safety Through Post-Post-Training Alignment

AI21’s AI Code of Conduct

Jamba-1.5: Hybrid Transformer-Mamba Models at Scale

Jamba: A Hybrid Transformer-Mamba Language Model

Parallel Context Windows for Large Language Models

In-Context Retrieval-Augmented Language Models

Generating Benchmarks for Factuality Evaluation of Language Models

Human or Not? A Gamified Approach to the Turing Test

AI21 Summarise API: Technial Evaluation

Grounding Language Models In-Context: Improving Text Generation and Attribution for Off-the-Shelf LMs

Auxiliary Tuning and its Application to Conditional Text Generation

PMI-Masking

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

1 2