Final-Model-Only Data Attribution with a Unifying View of Gradient-Based MethodsDennis WeiInkit Padhiet al.2024NeurIPS 2024
Value Alignment from Unstructured TextInkit PadhiKarthikeyan Natesan Ramamurthyet al.2024NeurIPS 2024
Split, Unlearn, Merge: Leveraging Data Attributes for More Effective Unlearning in LLMsSwanand Ravindra KadheFarhan Ahmedet al.2024ICML 2024
Auditing and Generating Synthetic Data With Controllable Trust Trade-OffsBrian BelgoderePierre Dogninet al.2024IEEE JESTCS
Alignment Studio: Aligning Large Language Models to Particular Contextual RegulationsSwapnaja AchintalwarIoana Baldiniet al.2024IEEE Internet Computing
The Impact of Positional Encoding on Length Generalization in TransformersAmirhossein KazemnejadInkit Padhiet al.2023NeurIPS 2023
Influence Based Approaches to Algorithmic Fairness: A Closer LookSoumya GhoshPrasanna Sattigeriet al.2023NeurIPS 2023
Reprogramming Pretrained Language Models for Antibody Sequence InfillingIgor MelnykVijil Chenthamarakshanet al.2023ICML 2023
07 Nov 2022US11494802Guiding Customized Textual Persuasiveness To Meet Persuasion Objectives Of A Communication At Multiple Levels
An AI foundation model that learns the grammar of molecules NewsPayel Das, Youssef Mroueh, Inkit Padhi, Vijil Chenthamarakshan, Jerret Ross, and Brian Belgodere25 Jan 2023Accelerated DiscoveryAIFoundation ModelsLife SciencesMaterials Discovery
IBM researchers check AI bias with counterfactual textResearchInkit Padhi, Nishtha Madaan, Naveen Panwar, and Diptikalyan Saha05 Feb 20215 minute readAI TestingFairness, Accountability, Transparency