Inkit Padhi

ML & NLP Researcher @ IBM Research, New York

profile_pic.png

Hi! My name is Inkit. I’m a researcher interested in fields of Machine Learning (ML) and Natural Language Processing (NLP). My current work centers around improving the safety, reliability, and trustworthiness of Large Language Models (LLMs).

Currently, my primary focus and interests lie in safety/alignment, synthetic data generation, steering and influence-based attributions within LLMs.

My past research has encompassed various areas of deep learning, including but not limited to, learning representations for diverse modalities, counterfactual generation, interpretability, text style transfer, unsupervised learning, and more. I began my research journey at USC/ISI under the guidance of Kevin Knight; our work on probing in sequence models established a foundational contribution in the field of interpretability.

Email: $first_name.$last_name@gmail.com

Updates

Dec, 2024 Attending NeurIPS ‘24 to present our work at the Pluralistic Alignment workshop.
Dec, 2024 Granite Guardian 3.0 technical report is now out!
Nov, 2024 I’ll be presenting our work “Value Alignment From Unstructured Text” at EMNLP 2024
Oct, 2024 Granite Guardian 3.0 is out! It helps detect input and response risks, including various harm and RAG hallucinations.
Sep, 2024 CAST: Checkout my exceptional summer intern, Bruce Lee’s, work on conditional activation steering.
Aug, 2024 Alignment Studio is accepted to IEEE Internet Computing! We introduce an architecture that facilitates alignment of LMs to specific values, norms and regulations within a context.

Selected Publications

A brief glimpse into things I've scribbled. For a comprehensive list, please refer to this page.
  1. Value Alignment from Unstructured Text
    Inkit Padhi, Karthikeyan Natesan Ramamurthy, Prasanna Sattigeri, and 3 more authors
    In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track, Nov 2024
  2. Programming Refusal with Conditional Activation Steering
    Bruce W. Lee, Inkit Padhi, Karthikeyan Natesan Ramamurthy, and 4 more authors
    Nov 2024
  3. ComVas: Contextual Moral Values Alignment System
    Inkit Padhi, Pierre Dognin, Jesus Rios, and 8 more authors
    In Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, IJCAI-24, Aug 2024
    Demo Track
    DOI
  4. The Impact of Positional Encoding on Length Generalization in Transformers
    Amirhossein Kazemnejad, Inkit Padhi, Karthikeyan Natesan Ramamurthy, and 2 more authors
    In Advances in Neural Information Processing Systems, Aug 2023
  5. Tabular Transformers for Modeling Multivariate Time Series
    Inkit Padhi, Yair Schiff, Igor Melnyk, and 6 more authors
    In ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Jun 2021
    DOI
  6. Does String-Based Neural MT Learn Source Syntax?
    Xing Shi, Inkit Padhi, and Kevin Knight
    In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, Nov 2016
    DOI