Apurv Verma

Profile

I am an AI Researcher with a primary interest in Natural Language Processing. I am currently interested in AI Safety, Alignment, Reasoning, and AI Content Detection. I am a Senior ML Engineer at Bloomberg Law, focusing on AI Safety in the Legal domain. I am also a Ph.D. student at NJIT.

Previously, I was an Applied Scientist at Amazon Alexa AI (2017-2023) where I had the opportunity to work on various NLU problems ranging from semantic parsing, multi-lingual modeling to tackling the bias and fairness issue in machine learning systems.

I received my Master's from Georgia Tech, advised by Professor Le Song. Before that, I worked as an engineer at Bloomreach, where I worked on clickstream data processing and search relevance. I obtained my Bachelor's in Computer Science from IIT Ropar, advised by Professor Apurva Mudgal.

I am originally from Northern India. I spent my early childhood close to forests on the India-Nepal border. Before starting my Computer Science journey, I wanted to be a physicist. In addition to my research interests, I love to cook, bike, read, learn piano, and occasionally travel. Feel free to reach out (via email) to chat about potential collaborations!

Find the latest on my website: https://vermaapurv.com/aboutme/

Publications

Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)

Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)

Apurv Verma, Satyapriya Krishna, Sebastian Gehrmann, Madhavan Seshadri, Anu Pradhan, Tom Ault, Leslie Barrett, David Rabinowitz, John Doucette, Nhathai Phan

arXiv.org 2024

ABSPDF

Incorporating Fairness in Large Scale NLU Systems

Rahul Gupta, Lisa Bauer, Kai-Wei Chang, J. Dhamala, A. Galstyan, Palash Goyal, Qian Hu, Avni Khatri, Rohit Parimi, Charith Peris, Apurv Verma, R. Zemel, Premkumar Natarajan

Web Search and Data Mining 2023

ABS

Is the Elephant Flying? Resolving Ambiguities in Text-to-Image Generative Models

Ninareh Mehrabi, Palash Goyal, Apurv Verma, J. Dhamala, Varun Kumar, Qian Hu, Kai-Wei Chang, R. Zemel, A. Galstyan, Rahul Gupta

arXiv.org 2022

ABSPDF
AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model

AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model

Saleh Soltan, Shankar Ananthakrishnan, Jack G. M. FitzGerald, Rahul Gupta, Wael Hamza, Haidar Khan, Charith Peris, Stephen Rawls, Andrew Rosenbaum, Anna Rumshisky, Chandan Prakash, Mukund Sridhar, Fabian Triefenbach, Apurv Verma, Gokhan Tur, Premkumar Natarajan

arXiv.org 2022

ABSPDF
Mitigating Gender Bias in Distilled Language Models via Counterfactual Role Reversal

Mitigating Gender Bias in Distilled Language Models via Counterfactual Role Reversal

Umang Gupta, J. Dhamala, Varun Kumar, Apurv Verma, Yada Pruksachatkun, Satyapriya Krishna, Rahul Gupta, Kai-Wei Chang, G. V. Steeg, A. Galstyan

Findings 2022

ABSPDF
Measuring Fairness of Text Classifiers via Prediction Sensitivity

Measuring Fairness of Text Classifiers via Prediction Sensitivity

Satyapriya Krishna, Rahul Gupta, Apurv Verma, J. Dhamala, Yada Pruksachatkun, Kai-Wei Chang

Annual Meeting of the Association for Computational Linguistics 2022

ABSPDF
Detecting Changes in Dynamic Events Over Networks

Detecting Changes in Dynamic Events Over Networks

Shuang Li, Yao Xie, Mehrdad Farajtabar, Apurv Verma, Le Song

IEEE Transactions on Signal and Information Processing over Networks 2017

ABS

A Stochastic Differential Equation Framework for Guiding Online User Activities in Closed Loop

Yichen Wang, Evangelos A. Theodorou, Apurv Verma, Le Song

International Conference on Artificial Intelligence and Statistics 2016

Steering Opinion Dynamics in Information Diffusion Networks

Steering Opinion Dynamics in Information Diffusion Networks

Yichen Wang, Evangelos A. Theodorou, Apurv Verma, Le Song

arXiv.org 2016

A Stochastic Differential Equation Framework for Guiding Information Diffusion

A Stochastic Differential Equation Framework for Guiding Information Diffusion

Yichen Wang, Evangelos A. Theodorou, Apurv Verma, Le Song

ABSPDF
Resolving Ambiguities in Text-to-Image Generative Models

Resolving Ambiguities in Text-to-Image Generative Models

Ninareh Mehrabi, Palash Goyal, Apurv Verma, J. Dhamala, Varun Kumar, Qian Hu, Kai-Wei Chang, R. Zemel, A. Galstyan, Rahul Gupta

Annual Meeting of the Association for Computational Linguistics 2023

ABSPDF
PG-Story: Taxonomy, Dataset, and Evaluation for Ensuring Child-Safe Content for Story Generation

PG-Story: Taxonomy, Dataset, and Evaluation for Ensuring Child-Safe Content for Story Generation

Alicia Tsai, Shereen Oraby, Anjali Narayan-Chen, Alessandra Cervone, Spandana Gella, Apurv Verma, Tagyoung Chung, Jing Huang, Nanyun Peng

NLP4PI 2024

ABS