resources

Resource library

Explore our complete library of resources including blogs, benchmarks, research papers and more.
Image for Evaluating Coding Agent Capabilities with Terminal-Bench: Snorkel’s Role in Building the Next Generation Benchmark
Blog

Evaluating Coding Agent Capabilities with Terminal-Bench: Snorkel’s Role in Building the Next Generation Benchmark

Announcing a $3M commitment to launch Open Benchmarks Grants
September 30, 2025
Image for Closing the Evaluation Gap in Agentic AI
Blog

Closing the Evaluation Gap in Agentic AI

Announcing a $3M commitment to launch Open Benchmarks Grants

February 11, 2026
Image for Benchtalks #1: Alex Shaw (Terminal-Bench, Harbor) – Building the Benchmark Factory
Blog

Benchtalks #1: Alex Shaw (Terminal-Bench, Harbor) – Building the Benchmark Factory

Announcing a $3M commitment to launch Open Benchmarks Grants
March 31, 2026
Image for Building FinQA: An Open RL Environment for Financial Reasoning Agents
Blog

Building FinQA: An Open RL Environment for Financial Reasoning Agents

Announcing a $3M commitment to launch Open Benchmarks Grants
March 30, 2026
Image for The science of rubric design
Blog

The science of rubric design

Announcing a $3M commitment to launch Open Benchmarks Grants
September 11, 2025
of
Type: All Types
Sort: Newest
Research spotlight: is long chain-of-thought structure all that matters when it comes to LLM reasoning distillation?
Blog
Research spotlight: is long chain-of-thought structure all that matters when it comes to LLM reasoning distillation?

We’re taking a look at the research paper, LLMs can easily learn to reason from demonstration (Li et al., 2025), in this week’s community research spotlight. It focuses on how the structure of reasoning traces impacts distillation from models such as DeepSeek R1. What’s the big idea regarding LLM reasoning distillation? The reasoning capabilities of powerful models such as DeepSeek…

Mar 19, 2025
Learn more about Research spotlight: is long chain-of-thought structure all that matters when it comes to LLM reasoning distillation?
Why enterprise GenAI evaluation requires fine-grained metrics to be insightful
Blog
Why enterprise GenAI evaluation requires fine-grained metrics to be insightful

GenAI needs fine-grained evaluation for AI teams to gain actionable insights.

Mar 18, 2025
Learn more about Why enterprise GenAI evaluation requires fine-grained metrics to be insightful
What is specialized GenAI evaluation, and why is it so critical to enterprise AI?
Blog
What is specialized GenAI evaluation, and why is it so critical to enterprise AI?

Specialized GenAI evaluation ensures AI assistants meet business requirements, SME expertise, and industry regulations—critical for production-ready AI.

Mar 05, 2025
Learn more about What is specialized GenAI evaluation, and why is it so critical to enterprise AI?
LLM alignment techniques: 4 post-training approaches
Blog
LLM alignment techniques: 4 post-training approaches

Ensure your LLMs align with your values and goals using LLM alignment techniques. Learn how to mitigate risks and optimize performance.

Mar 04, 2025
Learn more about LLM alignment techniques: 4 post-training approaches
Webinar
Improving the accuracy of domain-specific tasks with LLM distillation

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.

Mar 03, 2025
Snorkel Team
Learn more about Improving the accuracy of domain-specific tasks with LLM distillation
Weak-to-Strong Generalization Through the Data-Centric Lens
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, generalization tracks the number of points that contain overlaps, i.e., both easy patterns (learnable by a weak model) and challenging patterns (only learnable by a stronger model), as with such points, weak predictions can be used to learn challenging patterns...
Research Paper
Weak-to-Strong Generalization Through the Data-Centric Lens

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,…

Mar 01, 2025

Changho Shin, John Cooper, Frederic Sala Department of Computer Science University of Wisconsin-Madison

Learn more about Weak-to-Strong Generalization Through the Data-Centric Lens
Research spotlight: Is intent analysis the key to unlocking more accurate LLM question answering?
Blog
Research spotlight: Is intent analysis the key to unlocking more accurate LLM question answering?

Learn how ARR improves QA accuracy in LLMs through intent analysis, retrieval, and reasoning. Is intent the key to smarter AI? Explore ARR results!

Feb 27, 2025
Learn more about Research spotlight: Is intent analysis the key to unlocking more accurate LLM question answering?
Why enterprises should embrace LLM distillation
Blog
Why enterprises should embrace LLM distillation

Unlock possibilities for your enterprise with LLM distillation. Learn how distilled, task-specific models boost performance and shrink costs.

Feb 18, 2025
Learn more about Why enterprises should embrace LLM distillation
Retrieval-augmented generation (RAG) failure modes and how to fix them
Blog
Retrieval-augmented generation (RAG) failure modes and how to fix them

Discover common RAG failure modes and how to fix them. Learn how to optimize retrieval-augmented generation systems for max business value.

Feb 05, 2025
Learn more about Retrieval-augmented generation (RAG) failure modes and how to fix them
1 6 7 8 64
Image
Image

Join our newsletter

For expert advice, the latest research, and exclusive events.
By submitting this form, I acknowledge I will receive email updates from Snorkel AI, and I agree to the Terms of Use and acknowledge that my information will be used in accordance with the Privacy Policy.