R3 : Refined Retriever-Reader pipeline for Multidoc2dial

no code implementations • dialdoc (ACL) 2022 • Srijan Bansal, Suraj Tripathi, Sumit Agarwal, Sireesh Gururaja, Aditya Srikanth Veerubhotla, Ritam Dutt, Teruko Mitamura, Eric Nyberg

In this paper, we present our submission to the DialDoc shared task based on the MultiDoc2Dial dataset.

Conversational Question Answering Passage Retrieval +1

PEFTDebias : Capturing debiasing information using PEFTs

no code implementations • 1 Dec 2023 • Sumit Agarwal, Aditya Srikanth Veerubhotla, Srijan Bansal

The increasing use of foundation models highlights the urgent need to address and eliminate implicit biases present in them that arise during pretraining.

Few Shot Rationale Generation using Self-Training with Dual Teachers

no code implementations • 5 Jun 2023 • Aditya Srikanth Veerubhotla, Lahari Poddar, Jun Yin, György Szarvas, Sharanya Eswaran

Self-rationalizing models that also generate a free-text explanation for their predicted labels are an important tool to build trustworthy AI applications.

Few-Shot Learning