Resource library
Evaluating Coding Agent Capabilities with Terminal-Bench: Snorkel’s Role in Building the Next Generation Benchmark
Closing the Evaluation Gap in Agentic AI
Announcing a $3M commitment to launch Open Benchmarks Grants
Benchtalks #1: Alex Shaw (Terminal-Bench, Harbor) – Building the Benchmark Factory
Building FinQA: An Open RL Environment for Financial Reasoning Agents
This paper demonstrates a mathematical analysis of zero-shot learning with attributes, providing a tight lower bound on the worst-case error of the best map from attributes to classes and showing that this bound is predictive of how standard zero-shot methods behave in practice.
AutoWS-Bench-101 is a framework for evaluating automated weak supervision techniques compared to other baseline methods such as zero-shot foundation models and supervised learning, in order to help practitioners choose the best method to generate additional labels.
This paper finds that weak supervision can be used beyond classification applications, including rankings, graphs, and manifolds, and can provide generalization guarantees nearly identical to models trained on clean data.
This paper proposes source-aware variation of Influence Function, which measures the influence of individual components in the Programmatic Weak Supervision pipeline, and can be used for multiple purposes such as understanding incorrect predictions, identifying mislabeling of sources, and improving the end model’s generalization performance.
BigBIO is a community library of biomedical NLP datasets that facilitates meta-dataset curation and enables zero-shot evaluation of biomedical prompts and multi-task learning.
This work proposes and theoretically justifies a model that fuses weak supervision and generative adversarial networks to improve the estimate of unobserved labels and data augmentation, outperforming baseline weak supervision models on multiclass image classification datasets.
Liger, a combination of foundation models and weak supervision frameworks, improves existing weak supervision techniques by partitioning the embedding space and extending source votes in embedding space, resulting in improved performance on six benchmark NLP and video tasks.
This paper presents Nemo, an interactive system that improves the overall productivity of Weak Supervision learning pipelines by an average of 20%, compared to the prevailing WS approach.
This paper presents a comprehensive survey of recent advances in Programmatic Weak Supervision (PWS), and discusses related approaches to tackle limited labeled data scenarios.
