Resource library

Stanford researchers concluded that new, larger and more powerful foundation models represent a paradigm shift in AI, providing opportunities and risks that require deep interdisciplinary collaboration to understand and address.

This paper proposes “Ask Me Anything” (AMA), a prompting method that uses weak supervision to combine noisy predictions from multiple prompts generated from an LLM, resulting in an average 10.2% performance lift over the few-shot baseline across a variety of different open-source models.

The authors propose Contrastive Adapting, an efficient adapter training strategy that improves the group robustness of large pretrained foundation models (FMs) without finetuning, leading to up to 56.0 percentage points of increase in accuracy compared to zero-shot.

Zero-shot learning with Common Sense Knowledge Graphs is a general-purpose framework with a novel transformer graph convolutional network for generating class representations from common sense knowledge graphs, which improves over existing WordNet-based methods on zero-shot learning tasks.

This paper demonstrates that WEAPO, a Weak Supervision method for binary classification tasks with only positive labeling sources, is effective and efficient—achieving the highest performance of the tested Weak Supervision approaches in terms of label quality and final classifier accuracy on 10 benchmark datasets.

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.