337 citations · 427 across the 18 of their papers we have counts for
19 papers
XLGoBench: Detecting cross-lingual skill gaps with algorithmic tasks
Purvam Jain, Preethi Jyothi, Vihari Piratla +1
We introduce a set of synthetic algorithmic tasks to detect cross-lingual gaps in the abilities of large language models. Our benchmark is commensurate across languages, since it r…
Rethinking Cross-lingual Gaps from a Statistical Viewpoint
Vihari Piratla, Purvam Jain, Darshan Singh +3
Any piece of knowledge is usually expressed in one or a handful of natural languages on the web or in any large corpus. Large Language Models (LLMs) act as a bridge by acquiring kn…
Model Guidance via Robust Feature Attribution
Mihnea Ghitu, Vihari Piratla, Matthew Wicker
Controlling the patterns a model learns is essential to preventing reliance on irrelevant or misleading features. Such reliance on irrelevant features, often called shortcut featur…
Estimation of Concept Explanations Should be Uncertainty Aware
Vihari Piratla, Juyeon Heo, Katherine M. Collins +2
Model explanations can be valuable for interpreting and debugging predictive models. We study a specific kind called Concept Explanations, where the goal is to interpret a model us…
Certification of Distributional Individual Fairness
Matthew Wicker, Vihari Piratia, Adrian Weller
Providing formal guarantees of algorithmic fairness is of paramount importance to socially responsible deployment of machine learning algorithms. In this work, we study formal guar…
Robustness, Evaluation and Adaptation of Machine Learning Models in the Wild
Vihari Piratla
Our goal is to improve reliability of Machine Learning (ML) systems deployed in the wild. ML models perform exceedingly well when test examples are similar to train examples. Howev…
Use Perturbations when Learning from Explanations
Juyeon Heo, Vihari Piratla, Matthew Wicker +1
Machine learning from explanations (MLX) is an approach to learning that uses human-provided explanations of relevant or irrelevant features for each input to ensure that model pre…
Implicit Training of Energy Model for Structure Prediction
Shiv Shankar, Vihari Piratla
Most deep learning research has focused on developing new model and training procedures. On the other hand the training objective has usually been restricted to combinations of sta…
Human-in-the-Loop Mixup
Katherine M. Collins, Umang Bhatt, Weiyang Liu +4
Aligning model representations to humans has been found to improve robustness and generalization. However, such methods often focus on standard observational data. Synthetic data i…
Focus on the Common Good: Group Distributional Robustness Follows
Vihari Piratla, Praneeth Netrapalli, Sunita Sarawagi
We consider the problem of training a classification model with group annotated training data. Recent work has established that, if there is distribution shift across different gro…
Training for the Future: A Simple Gradient Interpolation Loss to Generalize Along Time
Anshul Nasery, Soumyadeep Thakur, Vihari Piratla +2
In several real world applications, machine learning models are deployed to make predictions on data whose distribution changes gradually along time, leading to a drift between the…
Active Assessment of Prediction Services as Accuracy Surface Over Attribute Combinations
Vihari Piratla, Soumen Chakrabarty, Sunita Sarawagi
Our goal is to evaluate the accuracy of a black-box classification model, not as a single aggregate on a given test data distribution, but as a surface over a large number of combi…
An Analysis of Frame-skipping in Reinforcement Learning
Shivaram Kalyanakrishnan, Siddharth Aravindan, Vishwajeet Bagdawat +5
In the practice of sequential decision making, agents are often designed to sense state at regular intervals of time steps, , ignoring state information in between sensi…
NLP Service APIs and Models for Efficient Registration of New Clients
Sahil Shah, Vihari Piratla, Soumen Chakrabarti +1
State-of-the-art NLP inference uses enormous neural architectures and models trained for GPU-months, well beyond the reach of most consumers of NLP. This has led to one-size-fits-a…
Untapped Potential of Data Augmentation: A Domain Generalization Viewpoint
Vihari Piratla, Shiv Shankar
Data augmentation is a popular pre-processing trick to improve generalization accuracy. It is believed that by processing augmented inputs in tandem with the original ones, the mod…
Efficient Domain Generalization via Common-Specific Low-Rank Decomposition
Vihari Piratla, Praneeth Netrapalli, Sunita Sarawagi
Domain generalization refers to the task of training a model which generalizes to new domains that are not seen during training. We present CSD (Common Specific Decomposition), for…
Parallel Iterative Edit Models for Local Sequence Transduction
Abhijeet Awasthi, Sunita Sarawagi, Rasna Goyal +2
We present a Parallel Iterative Edit (PIE) model for the problem of local sequence transduction arising in tasks like Grammatical error correction (GEC). Recent approaches are base…
Topic Sensitive Attention on Generic Corpora Corrects Sense Bias in Pretrained Embeddings
Vihari Piratla, Sunita Sarawagi, Soumen Chakrabarti
Given a small corpus pertaining to a limited set of focused topics, our goal is to train embeddings that accurately capture the sense of words in the topic in spite…
Generalizing Across Domains via Cross-Gradient Training
Shiv Shankar, Vihari Piratla, Soumen Chakrabarti +3
We present CROSSGRAD, a method to use multi-domain training data to learn a classifier that generalizes to new domains. CROSSGRAD does not need an adaptation phase via labeled or u…