Guides

Programmatically launch human data jobs for RLHF and evaluation

Learn how to harness the SDK to manage human data labeling jobs for RLHF and model evaluation. With just a few steps, you can set up the SDK, import various types of data, and launch, monitor, and export labeling projects programmatically, all while ensuring data quality and scalability.

Evaluating leading text-to-speech models

Discover how to employ a more comprehensive approach to evaluating leading text-to-speech models using both human preference ratings and automated evaluation techniques.

Metrics-based RAG Development with Labelbox

Learn how to optimize your Retrieval-Augmented Generation (RAG) applications by focusing on key metrics like context recall and precision.

Unlocking precision: The "Needle-in-a-Haystack" test for LLM evaluation

Discover how to choose the perfect large language model for your pre-labeling tasks by diving into our "Needle-in-a-Haystack" experiment. Learn how to enhance accuracy and efficiency in complex data annotations.

A comprehensive approach to evaluating text-to-video models

Discover how to employ a more comprehensive approach to evaluating leading text-to-video models using human preference ratings, as well as challenges with automated evaluation techniques.

A comprehensive approach to evaluating text-to-image models

Discover how to employ a more comprehensive approach to evaluating leading text-to-image models using both human preference ratings and automated evaluation techniques.

Using Labelbox to improve data quality via AutoQA & advanced labeler review

Learn how you can use Labelbox to accelerate the quality review process for creating better data for generative AI use cases using autoQA and advanced labeler reviews.

Using multimodal chat to enhance a customer’s online support experience

In this guide we’ll show how Labelbox can be used to collect training data for an ecommerce chatbot that responds to customer queries about online shopping.

Working with videos using Gemini 1.5 and multimodal models

Introduction  Given the pace of innovation in AI, teams are continually looking to integrate various data types like text, images, and video as a way to unlock new functionality for delivering next-gen applications and experiences. The development of multimodal models, which can process and understand diverse data inputs, is one of the most promising advancements.  Notably, combining video processing with the capabilities of large language models (LLMs) is a breakthrough feature for teams who

AI foundations: Understanding embeddings

Learn how to utilize embeddings for data vector representations and discover key use cases at Labelbox, including uploading custom embeddings for optimized performance.