papers

Publications (12)

cs.LG2023

Collaborative Development of NLP models

Fereshte Khani, Marco Tulio Ribeiro

Despite substantial advancements, Natural Language Processing (NLP) models often require post-training adjustments to enforce business rules, rectify undesired behavior, and align…

cs.LG2016

Unanimous Prediction for 100% Precision with Application to Learning Semantic Mappings

Fereshte Khani, Martin Rinard, Percy Liang

Can we train a system that, on any new input, either says "don't know" or makes a prediction that is guaranteed to be correct? We answer the question in the affirmative provided ou…

cs.CL2023

Targeted Data Generation: Finding and Fixing Model Weaknesses

Zexue He, Marco Tulio Ribeiro, Fereshte Khani

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. Addi…

cs.LG2020

Feature Noise Induces Loss Discrepancy Across Groups

Fereshte Khani, Percy Liang

The performance of standard learning procedures has been observed to differ widely across groups. Recent studies usually attribute this loss discrepancy to an information deficienc…

cs.CL2018

Planning, Inference and Pragmatics in Sequential Language Games

Fereshte Khani, Noah D. Goodman, Percy Liang

We study sequential language games in which two players, each with private information, communicate to achieve a common goal. In such games, a successful player must (i) infer the…

cs.LG2022

MaskTune: Mitigating Spurious Correlations by Forcing to Explore

Saeid Asgari Taghanaki, Aliasghar Khani, Fereshte Khani +4

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…

cs.LG2022

Counterbalancing Teacher: Regularizing Batch Normalized Models for Robustness

Saeid Asgari Taghanaki, Ali Gholami, Fereshte Khani +4

Batch normalization (BN) is a ubiquitous technique for training deep neural networks that accelerates their convergence to reach higher accuracy. However, we demonstrate that BN co…

cs.CL2024

Prompt Engineering a Prompt Engineer

Qinyuan Ye, Maxamed Axmed, Reid Pryzant +1

Prompt engineering is a challenging yet crucial task for optimizing the performance of large language models on customized tasks. It requires complex reasoning to examine the model…

cs.LG2022

On the Opportunities and Risks of Foundation Models

Rishi Bommasani, Drew A. Hudson, Ehsan Adeli +111

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.…

cs.LG2020

Removing Spurious Features can Hurt Accuracy and Affect Groups Disproportionately

Fereshte Khani, Percy Liang

The presence of spurious features interferes with the goal of obtaining robust models that perform well across many groups within the population. A natural remedy is to remove spur…

cs.LG2019

Maximum Weighted Loss Discrepancy

Fereshte Khani, Aditi Raghunathan, Percy Liang

Though machine learning algorithms excel at minimizing the average loss over a population, this might lead to large discrepancies between the losses across groups within the popula…

cs.LG2021

In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness

Sang Michael Xie, Ananya Kumar, Robbie Jones +3

Consider a prediction setting with few in-distribution labeled examples and many unlabeled examples both in- and out-of-distribution (OOD). The goal is to learn a model which perfo…