786 citations · 1.9k across the 20 of their papers we have counts for
21 papers
Enhancing CLIP with CLIP: Exploring Pseudolabeling for Limited-Label Prompt Tuning
Cristina Menghini, Andrew Delworth, Stephen H. Bach
Fine-tuning vision-language models (VLMs) like CLIP to downstream tasks is often necessary to optimize their performance. However, a major obstacle is the limited availability of l…
An Adaptive Method for Weak Supervision with Drifting Data
Alessio Mazzetto, Reza Esfandiarpoor, Akash Singirikonda +2
We introduce an adaptive method with formal quality guarantees for weak supervision in a non-stationary setting. Our goal is to infer the unknown labels of a sequence of data by us…
Alfred: A System for Prompted Weak Supervision
Peilin Yu, Stephen H. Bach
Alfred is the first system for programmatic weak supervision (PWS) that creates training data for machine learning by prompting. In contrast to typical PWS systems where weak super…
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model
BigScience Workshop, :, Teven Le Scao +391
Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions. While these capabilities have led to wi…
Fairness via Explanation Quality: Evaluating Disparities in the Quality of Post hoc Explanations
Jessica Dai, Sohini Upadhyay, Ulrich Aivodji +2
As post hoc explanation methods are increasingly being leveraged to explain complex models in high-stakes settings, it becomes critical to ensure that the quality of the resulting…
BigBIO: A Framework for Data-Centric Biomedical Natural Language Processing
Jason Alan Fries, Leon Weber, Natasha Seelam +40
Training and evaluating language models increasingly requires the construction of meta-datasets --diverse collections of curated data with clear provenance. Natural language prompt…
Language Models in the Loop: Incorporating Prompting into Weak Supervision
Ryan Smith, Jason A. Fries, Braden Hancock +1
We propose a new strategy for applying large pre-trained language models to novel tasks when labeled training data is limited. Rather than apply the model in a typical zero-shot or…
Tight Lower Bounds on Worst-Case Guarantees for Zero-Shot Learning with Attributes
Alessio Mazzetto, Cristina Menghini, Andrew Yuan +2
We develop a rigorous mathematical analysis of zero-shot learning with attributes. In this setting, the goal is to label novel classes with no training data, only detectors for att…
Learning to Compose Soft Prompts for Compositional Zero-Shot Learning
Nihal V. Nayak, Peilin Yu, Stephen H. Bach
We introduce compositional soft prompting (CSP), a parameter-efficient learning technique to improve the zero-shot compositionality of large-scale pretrained vision-language models…
PromptSource: An Integrated Development Environment and Repository for Natural Language Prompts
Stephen H. Bach, Victor Sanh, Zheng-Xin Yong +24
PromptSource is a system for creating, sharing, and using natural language prompts. Prompts are functions that map an example from a dataset to a natural language input and target…
TAGLETS: A System for Automatic Semi-Supervised Learning with Auxiliary Data
Wasu Piriyakulkij, Cristina Menghini, Ross Briden +4
Machine learning practitioners often have access to a spectrum of data: labeled data for the target task (which is often limited), unlabeled data, and auxiliary data, the many avai…
Multitask Prompted Training Enables Zero-Shot Task Generalization
Victor Sanh, Albert Webson, Colin Raffel +38
Large language models have recently been shown to attain reasonable zero-shot generalization on a diverse set of tasks (Brown et al., 2020). It has been hypothesized that this is a…
What will it take to generate fairness-preserving explanations?
Jessica Dai, Sohini Upadhyay, Stephen H. Bach +1
In situations where explanations of black-box models may be useful, the fairness of the black-box is also often a relevant concern. However, the link between the fairness of the bl…
Learning from Multiple Noisy Partial Labelers
Peilin Yu, Tiffany Ding, Stephen H. Bach
Programmatic weak supervision creates models without hand-labeled training data by combining the outputs of heuristic labelers. Existing frameworks make the restrictive assumption…
Extended Few-Shot Learning: Exploiting Existing Resources for Novel Tasks
Reza Esfandiarpoor, Amy Pu, Mohsen Hajabdollahi +1
In many practical few-shot learning problems, even though labeled examples are scarce, there are abundant auxiliary datasets that potentially contain useful information. We propose…
Zero-Shot Learning with Common Sense Knowledge Graphs
Nihal V. Nayak, Stephen H. Bach
Zero-shot learning relies on semantic class representations such as hand-engineered attributes or learned embeddings to predict classes without any labeled examples. We propose to…
Snorkel DryBell: A Case Study in Deploying Weak Supervision at Industrial Scale
Stephen H. Bach, Daniel Rodriguez, Yintao Liu +10
Labeling training data is one of the most costly bottlenecks in developing machine learning-based applications. We present a first-of-its-kind study showing how existing knowledge…
Snorkel: Rapid Training Data Creation with Weak Supervision
Alexander Ratner, Stephen H. Bach, Henry Ehrenberg +3
Labeling training data is increasingly the largest bottleneck in deploying machine learning systems. We present Snorkel, a first-of-its-kind system that enables users to train stat…
Learning the Structure of Generative Models without Labeled Data
Stephen H. Bach, Bryan He, Alexander Ratner +1
Curating labeled training data has become the primary bottleneck in machine learning. Recent frameworks address this bottleneck with generative models to synthesize labels at scale…
Hinge-Loss Markov Random Fields and Probabilistic Soft Logic
Stephen H. Bach, Matthias Broecheler, Bert Huang +1
A fundamental challenge in developing high-impact machine learning technologies is balancing the need to model rich, structured domains with the ability to scale to big data. Many…
Hinge-loss Markov Random Fields: Convex Inference for Structured Prediction
Stephen Bach, Bert Huang, Ben London +1
Graphical models for structured domains are powerful tools, but the computational complexities of combinatorial prediction spaces can force restrictions on models, or require appro…