Search Results for author:
Found 23 papers, 15 papers with code
Mapping the Increasing Use of LLMs in Scientific Papers
To address this gap, we conduct the first systematic, large-scale analysis across 950, 965 papers published between January 2020 and February 2024 on the arXiv, bioRxiv, and Nature portfolio journals, using a population-level statistical framework to measure the prevalence of LLM-modified content over time.
Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews
We present an approach for estimating the fraction of text in a large corpus which is likely to be substantially modified or produced by a large language model (LLM).
What's documented in AI? Systematic Analysis of 32K AI Model Cards
To evaluate the impact of model cards, we conducted an intervention study by adding detailed model cards to 42 popular models which had no or sparse model cards previously.
Navigating Dataset Documentations in AI: A Large-Scale Analysis of Dataset Cards on Hugging Face
By analyzing all 7, 433 dataset documentation on Hugging Face, our investigation provides an overview of the Hugging Face dataset ecosystem and insights into dataset documentation practices, yielding 5 main findings: (1) The dataset card completion rate shows marked heterogeneity correlated with dataset popularity.
Can large language models provide useful feedback on research papers? A large-scale empirical analysis
We first quantitatively compared GPT-4's generated feedback with human peer reviewer feedback in 15 Nature family journals (3, 096 papers in total) and the ICLR machine learning conference (1, 709 papers).
Accuracy on the Curve: On the Nonlinear Correlation of ML Performance Between Data Subpopulations
Our work highlights the importance of understanding the nonlinear effects of model improvement on performance in different subpopulations, and has the potential to inform the development of more equitable and responsible machine learning models.
GPT detectors are biased against non-native English writers
In this study, we evaluate the performance of several widely-used GPT detectors using writing samples from native and non-native English writers.
SEAL : Interactive Tool for Systematic Error Analysis and Labeling
With the advent of Transformers, large language models (LLMs) have saturated well-known NLP benchmarks and leaderboards with high aggregate performance.
Data Budgeting for Machine Learning
Data is the fuel powering AI and creates tremendous value for many domains.
GSCLIP : A Framework for Explaining Distribution Shifts in Natural Language
Motivated by this, we propose a novel task, dataset explanation.
Disparities in Dermatology AI Performance on a Diverse, Curated Clinical Image Set
To ascertain potential biases in algorithm performance in this context, we curated the Diverse Dermatology Images (DDI) dataset-the first publicly available, expertly curated, and pathologically confirmed image dataset with diverse skin tones.
Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning
Our systematic analysis demonstrates that this gap is caused by a combination of model initialization and contrastive learning optimization.
MetaShift: A Dataset of Datasets for Evaluating Contextual Distribution Shifts and Training Conflicts
We present MetaShift--a collection of 12, 868 sets of natural images across 410 classes--to address this challenge.
Improving Out-of-Distribution Robustness via Selective Augmentation
Machine learning algorithms typically assume that training and test examples are drawn from the same distribution.
Disparities in Dermatology AI: Assessments Using Diverse Clinical Images
AI diagnostic tools may aid in early skin cancer detection; however most models have not been assessed on images of diverse skin tones or uncommon diseases.
HERALD: An Annotation Efficient Method to Detect User Disengagement in Social Conversations
Open-domain dialog systems have a user-centric goal: to provide humans with an engaging conversation experience.
GraghVQA: Language-Guided Graph Neural Networks for Graph-based Visual Question Answering
Images are more than a collection of objects or attributes -- they represent a web of relationships among interconnected objects.
Ranked #1 on
Graph Question Answering
on GQA
Neural Group Testing to Accelerate Deep Learning
A key challenge of neural group testing is to modify a deep neural network so that it could test multiple samples in one forward pass.
LRTA: A Transparent Neural-Symbolic Reasoning Framework with Modular Supervision for Visual Question Answering
We show that LRTA makes a step towards truly understanding the question while the state-of-the-art model tends to learn superficial correlations from the training data.
ALICE: Active Learning with Contrastive Natural Language Explanations
We propose Active Learning with Contrastive Explanations (ALICE), an expert-in-the-loop training framework that utilizes contrastive natural language explanations to improve data efficiency in learning.
Beyond User Self-Reported Likert Scale Ratings: A Comparison Model for Automatic Dialog Evaluation
Our experiments show that CMADE achieves 89. 2% accuracy in the dialog comparison task.
DAWSON: A Domain Adaptive Few Shot Generation Framework
Based on DAWSON, We also propose MUSIC MATINEE, which is the first few-shot music generation model.
MOSS: End-to-End Dialog System Framework with Modular Supervision
To utilize limited training data more efficiently, we propose Modular Supervision Network (MOSS), an encoder-decoder training framework that could incorporate supervision from various intermediate dialog system modules including natural language understanding, dialog state tracking, dialog policy learning, and natural language generation.
