Hi, I am Anubha Kabra
Artificial Intelligence | Natural Language Processing | Generative AI
I am a Senior Machine Learning Reserach Engineer at Bloomberg. I am currently exploring how to develop and use LLMs for industry and customer facing use cases.
I was a Master's Student in School of Computer Science at Carnegie Mellon University. My Advisor was Dr. Graham Neubig
I was in Language Technological Institute (LTI), studying and implementing very interesting concepts in Natural Language Processing and Artificial Intelligence.
Earlier, I worked as a software development engineer at Adobe. I aspire to contribute to community by developing cutting edge deployable products.
Organizations I have worked with :
Apple
R&D
Media and Data Science Research Lab Adobe
Adobe Experience Platform
Machine Learning Laboratory, Delhi Technological University
Exciting News
[May 2024] My work done for protecting the user-side privacy associated with online self-disclosure through identification and abstraction using Language Models - Reducing Privacy Risks in Online Self-Disclosures with Language Models is accepted in ACL 2024, Thailand!
[March 2024] My work on exploring calibration in different prompting styles have been accepted in NAACL, Mexico City! - Program-Aided Reasoners (better) Know What They Know.
[Jan 2024] I have joined Bloomberg as a Senior ML Research Engineer!
[Nov 2023] My work on exploring calibration in different prompting styles is now on Arxiv! - Program-Aided Reasoners (better) Know What They Know. In this paper, we compare the calibration of Program Aided Language Models (PAL) and text-based Chain-of-thought (COT) prompting techniques over 5 datasets and 2 model types: LLaMA models and OpenAI models. Our results indicate that PAL leads to improved calibration in 75% of the instances.
[Nov 2023] My work at CMU in collaboration with Georgia Tech is now on Arxiv! - Reducing Privacy Risks in Online Self-Disclosures with Language Models. In this paper, we take the initiative to protect the user-side privacy associated with online self-disclosure through identification and abstraction using Language Models
[Oct 2023] My work done in Carnegie Mellon University : "Counting the Bugs in ChatGPT's Wugs: A Multilingual Investigation into the Morphological Capabilities of a Large Language Model" got accepted in EMNLP 2023, Singapore!
[May 2023] My work done in Carnegie Mellon University : "Multi-lingual and Multi-cultural Figurative Language Understanding" got accepted in ACL 2023, Toronto, CA!
[May 2023] I have started working in Apple Research as an AI - ML intern for this summer at New York City!
[Feb 2023] My research at Delhi Technological University was awarded "Premier" and "Commendable" Research Awards. (Click to see the paper!)
[Aug 2022] Joined School of Computer Science, Carnegie Mellon University for pursuing a Master's Degree!
[Feb 2022] Awarded the prestigious Vector AI scholarship, by Vector Institute of AI, Canada!
Publications and Patents
Spotfake+: A multimodal framework for fake news detection via transfer learning (student abstract)
S Singhal, A Kabra*, M Sharma*, RR Shah, T Chakraborty, P Kumaraguru
Proceedings of the AAAI Conference on Artificial Intelligence, 2020
A Kabra *, Y Kumar *, M Bhatia*, JJ Li, D Jin, RR Shah
arXiv preprint arXiv:2007.06796 (2020)
Cluster-Based Deep Contextual Reinforcement Learning for Top-k Recommendations
A Kabra, A Agarwal, AS Parihar
Proceedings of the International Conference on Computing and Communication Systems: I3CS 2020, NEHU, Shillong, India - Springer (2020)
MixBoost: Synthetic Oversampling using Boosted Mixup for Handling Extreme Imbalance
A Kabra, A Chopra, N Puri, P Badjatiya, S Verma, P Gupta, Balaji Krishnamurthy
2020 IEEE International Conference on Data Mining (ICDM) (2020)
Feature Enhanced Capsule Networks for Robust Automatic Essay Scoring
A Sharma* , A Kabra* , R Kapoor
Joint European Conference on Machine Learning and Knowledge Discovery in Databases (Springer ECML-PKDD) (2021)
Potent Real-Time Recommendations Using Multi-Model Contextual Reinforcement Learning
A Kabra*, A Agarwal*, AS Parihar
IEEE Transactions on Computational Social Systems (2021)
Personalized and Dynamic top-k Recommendation System using Context Aware Deep Reinforcement Learning
A Kabra*, A Agarwal*
2021 IEEE 45th Annual Computers, Software, and Applications Conference (COMPSAC)
Entropy Based Synthetic Data Generation For Augmenting Classification System Training Data (PATENT) - 2020
A Kabra, P Badjatiya, N Puri, A Chopra
US Patent App. 16/659,147
MoH : Ceasing hate speech in code switched Hindi English text on social media.
A Kabra*, A.Sharma*, M. Jain
Elsevier Journal of Information Processing and Management 2021
*represents equal contribution
Skills
Python
Java
NLP
Node JS
Tensorflow
PyTorch
LLMs Large Language Models
Spring boot
LaTex
Azure Services
Projects
[2023] Privacy Mirror : Identifying disclosures on social media with human feedback.
[AAAI 2020] SPOTFAKE+ : Multimodal Fake News Detection