Resource library
Explore our complete library of resources including blogs, benchmarks, research papers, and more.
Why coding agents need better data, evals, and environments
Closing the Evaluation Gap in Agentic AI
Announcing a $3M commitment to launch Open Benchmarks Grants
Evaluating coding agent capabilities with Terminal-Bench: Snorkel’s role in building the next generation benchmark
Building FinQA: An Open RL Environment for Financial Reasoning Agents
The science of rubric design
Specialized GenAI evaluation ensures AI assistants meet business requirements, SME expertise, and industry regulations—critical for production-ready AI.
Ensure your LLMs align with your values and goals using LLM alignment techniques. Learn how to mitigate risks and optimize performance.
In this webinar, we’ll provide an overview of LLM distillation, explain how it compares with fine-tuning, and introduce the latest techniques for training SLMs using foundation models and knowledge transfer methods.
The weak-to-strong generalization phenomenon is the driver for important machine learning applications including highly data-efficient learning and, most recently, performing superalignment. While decades of research have resulted in numerous algorithms that produce strong empirical performance, understanding what aspects of data enable weak-to-strong generalization has been understudied. We propose a simple data-centric mechanism that characterizes weak-to-strong generalization: the overlap density. Intuitively,…
Learn how ARR improves QA accuracy in LLMs through intent analysis, retrieval, and reasoning. Is intent the key to smarter AI? Explore ARR results!
Unlock possibilities for your enterprise with LLM distillation. Learn how distilled, task-specific models boost performance and shrink costs.
Discover common RAG failure modes and how to fix them. Learn how to optimize retrieval-augmented generation systems for max business value.
We introduce a benchmark to evaluate the capability of AI to solve problems in theoretical physics, focusing on high-energy theory and cosmology. The first iteration of our benchmark consists of 57 problems of varying difficulty, from undergraduate to research level. These problems are novel in the sense that they do not come from public problem collections. We evaluate our data…
Learn how to evaluate GenAI systems, generate synthetic training data, and optimize retrieval with foundation models from Anthropic, Cohere, and Meta by taking advantage of native AWS Bedrock and SageMaker integration in Snorkel Flow.
