Lumos : Empowering Multimodal LLMs with Scene Text Recognition

no code implementations • 12 Feb 2024 • Ashish Shenoy, Yichao Lu, Srihari Jayakumar, Debojeet Chatterjee, Mohsen Moslehpour, Pierce Chuang, Abhay Harpale, Vikas Bhardwaj, Di Xu, Shicong Zhao, Longfang Zhao, Ankit Ramchandani, Xin Luna Dong, Anuj Kumar

We introduce Lumos, the first end-to-end multimodal question-answering system with text understanding capabilities.

Language Modelling Large Language Model +2

Improving Opinion-based Question Answering Systems Through Label Error Detection and Overwrite

no code implementations • 13 Jun 2023 • Xiao Yang, Ahmed K. Mohamed, Shashank Jain, Stanislav Peshterliev, Debojeet Chatterjee, Hanwen Zha, Nikita Bhalla, Gagan Aneja, Pranab Mohanty

Importantly, LEDO is computationally efficient compared to methods that require loss function change, and cost-effective as the resulting data can be used in the same continuous training pipeline for production.

Label Error Detection Machine Reading Comprehension +2

A Study on the Efficiency and Generalization of Light Hybrid Retrievers

no code implementations • 4 Oct 2022 • Man Luo, Shashank Jain, Anchit Gupta, Arash Einolghozati, Barlas Oguz, Debojeet Chatterjee, Xilun Chen, Chitta Baral, Peyman Heidari

Driven by this question, we leverage an indexing-efficient dense retriever (i. e. DrBoost) and introduce a LITE retriever that further reduces the memory of DrBoost.

Adversarial Attack Contrastive Learning +1

Conversational Answer Generation and Factuality for Reading Comprehension Question-Answering

no code implementations • 11 Mar 2021 • Stan Peshterliev, Barlas Oguz, Debojeet Chatterjee, Hakan Inan, Vikas Bhardwaj

A popular approach to QA is extractive reading comprehension (RC) which finds an answer span in a text passage.

Answer Generation Passage Ranking +2