Search Results for author:
Found 13 papers, 8 papers with code
Prompt Engineering a Prompt Engineer
While recent works indicate that large language models can be meta-prompted to perform automatic prompt engineering, we argue that their potential is limited due to insufficient guidance for complex reasoning in the meta-prompt.
Targeted Data Generation: Finding and Fixing Model Weaknesses
Even when aggregate accuracy is high, state-of-the-art NLP models often fail systematically on specific subgroups of data, resulting in unfair outcomes and eroding user trust.
Collaborative Development of NLP models
Our main insight is learning a \emph{local} model for each concept, and a \emph{global} model to integrate the original data with all concepts.
MaskTune: Mitigating Spurious Correlations by Forcing to Explore
A fundamental challenge of over-parameterized deep learning models is learning meaningful data representations that yield good performance on a downstream task without over-fitting spurious input features.
Counterbalancing Teacher: Regularizing Batch Normalized Models for Robustness
Batch normalization (BN) is a ubiquitous technique for training deep neural networks that accelerates their convergence to reach higher accuracy.
On the Opportunities and Risks of Foundation Models
AI is undergoing a paradigm shift with the rise of models (e. g., BERT, DALL-E, GPT-3) that are trained on broad data at scale and are adaptable to a wide range of downstream tasks.
In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness
To get the best of both worlds, we introduce In-N-Out, which first trains a model with auxiliary inputs and uses it to pseudolabel all the in-distribution inputs, then pre-trains a model on OOD auxiliary outputs and fine-tunes this model with the pseudolabels (self-training).
Removing Spurious Features can Hurt Accuracy and Affect Groups Disproportionately
The presence of spurious features interferes with the goal of obtaining robust models that perform well across many groups within the population.
Feature Noise Induces Loss Discrepancy Across Groups
Our main result is that even when there is no information deficiency specific to one group (e. g., both groups have infinite data), adding the same amount of feature noise to all individuals leads to loss discrepancy.
Maximum Weighted Loss Discrepancy
To capture this inequality, we introduce and study a notion we call maximum weighted loss discrepancy (MWLD), the maximum (weighted) difference between the loss of a group and the loss of the population.
Planning, Inference and Pragmatics in Sequential Language Games
We study sequential language games in which two players, each with private information, communicate to achieve a common goal.
Unanimous Prediction for 100% Precision with Application to Learning Semantic Mappings
Specifically, we introduce the unanimity principle: only predict when all models consistent with the training data predict the same output.
