Picture for Matthew R. Gormley

Matthew R. Gormley

A Taxonomy for Data Contamination in Large Language Models

Add code
Jul 11, 2024
Viaarxiv icon

In-Context Learning with Long-Context Models: An In-Depth Exploration

Add code
Apr 30, 2024
Figure 1 for In-Context Learning with Long-Context Models: An In-Depth Exploration
Figure 2 for In-Context Learning with Long-Context Models: An In-Depth Exploration
Figure 3 for In-Context Learning with Long-Context Models: An In-Depth Exploration
Figure 4 for In-Context Learning with Long-Context Models: An In-Depth Exploration
Viaarxiv icon

Learning Mutually Informed Representations for Characters and Subwords

Add code
Nov 14, 2023
Figure 1 for Learning Mutually Informed Representations for Characters and Subwords
Figure 2 for Learning Mutually Informed Representations for Characters and Subwords
Figure 3 for Learning Mutually Informed Representations for Characters and Subwords
Figure 4 for Learning Mutually Informed Representations for Characters and Subwords
Viaarxiv icon

It's MBR All the Way Down: Modern Generation Techniques Through the Lens of Minimum Bayes Risk

Add code
Oct 02, 2023
Figure 1 for It's MBR All the Way Down: Modern Generation Techniques Through the Lens of Minimum Bayes Risk
Figure 2 for It's MBR All the Way Down: Modern Generation Techniques Through the Lens of Minimum Bayes Risk
Figure 3 for It's MBR All the Way Down: Modern Generation Techniques Through the Lens of Minimum Bayes Risk
Figure 4 for It's MBR All the Way Down: Modern Generation Techniques Through the Lens of Minimum Bayes Risk
Viaarxiv icon

MDACE: MIMIC Documents Annotated with Code Evidence

Add code
Jul 07, 2023
Figure 1 for MDACE: MIMIC Documents Annotated with Code Evidence
Figure 2 for MDACE: MIMIC Documents Annotated with Code Evidence
Figure 3 for MDACE: MIMIC Documents Annotated with Code Evidence
Figure 4 for MDACE: MIMIC Documents Annotated with Code Evidence
Viaarxiv icon

SummQA at MEDIQA-Chat 2023:In-Context Learning with GPT-4 for Medical Summarization

Add code
Jun 30, 2023
Figure 1 for SummQA at MEDIQA-Chat 2023:In-Context Learning with GPT-4 for Medical Summarization
Figure 2 for SummQA at MEDIQA-Chat 2023:In-Context Learning with GPT-4 for Medical Summarization
Figure 3 for SummQA at MEDIQA-Chat 2023:In-Context Learning with GPT-4 for Medical Summarization
Figure 4 for SummQA at MEDIQA-Chat 2023:In-Context Learning with GPT-4 for Medical Summarization
Viaarxiv icon

Unlimiformer: Long-Range Transformers with Unlimited Length Input

Add code
May 02, 2023
Figure 1 for Unlimiformer: Long-Range Transformers with Unlimited Length Input
Figure 2 for Unlimiformer: Long-Range Transformers with Unlimited Length Input
Figure 3 for Unlimiformer: Long-Range Transformers with Unlimited Length Input
Figure 4 for Unlimiformer: Long-Range Transformers with Unlimited Length Input
Viaarxiv icon

Revisiting text decomposition methods for NLI-based factuality scoring of summaries

Add code
Nov 30, 2022
Figure 1 for Revisiting text decomposition methods for NLI-based factuality scoring of summaries
Figure 2 for Revisiting text decomposition methods for NLI-based factuality scoring of summaries
Figure 3 for Revisiting text decomposition methods for NLI-based factuality scoring of summaries
Figure 4 for Revisiting text decomposition methods for NLI-based factuality scoring of summaries
Viaarxiv icon

AdaFocal: Calibration-aware Adaptive Focal Loss

Add code
Nov 21, 2022
Figure 1 for AdaFocal: Calibration-aware Adaptive Focal Loss
Figure 2 for AdaFocal: Calibration-aware Adaptive Focal Loss
Figure 3 for AdaFocal: Calibration-aware Adaptive Focal Loss
Figure 4 for AdaFocal: Calibration-aware Adaptive Focal Loss
Viaarxiv icon

He Said, She Said: Style Transfer for Shifting the Perspective of Dialogues

Add code
Oct 27, 2022
Figure 1 for He Said, She Said: Style Transfer for Shifting the Perspective of Dialogues
Figure 2 for He Said, She Said: Style Transfer for Shifting the Perspective of Dialogues
Figure 3 for He Said, She Said: Style Transfer for Shifting the Perspective of Dialogues
Figure 4 for He Said, She Said: Style Transfer for Shifting the Perspective of Dialogues
Viaarxiv icon