Search Results for author: Shreyas Verma

Found 4 papers, 2 papers with code

FusionMind -- Improving question and answering with external context fusion

no code implementations31 Dec 2023 Shreyas Verma, Manoj Parmar, Palash Choudhary, Sanchita Porwal

Answering questions using pre-trained language models (LMs) and knowledge graphs (KGs) presents challenges in identifying relevant knowledge and performing joint reasoning. We compared LMs (fine-tuned for the task) with the previously published QAGNN method for the Question-answering (QA) objective and further measured the impact of additional factual context on the QAGNN performance.

Knowledge Graphs Multiple-choice +1

Reducing LLM Hallucinations using Epistemic Neural Networks

no code implementations25 Dec 2023 Shreyas Verma, Kien Tran, Yusuf Ali, Guangyu Min

ENNs are small networks attached to large, frozen models to improve the model's joint distributions and uncertainty estimates.

TarGEN: Targeted Data Generation with Large Language Models

1 code implementation27 Oct 2023 Himanshu Gupta, Kevin Scaria, Ujjwala Anantheswaran, Shreyas Verma, Mihir Parmar, Saurabh Arjun Sawant, Chitta Baral, Swaroop Mishra

Finally, when pre-finetuned on our synthetic SuperGLUE dataset, T5-3B yields impressive results on the OpenLLM leaderboard, surpassing the model trained on the Self-Instruct dataset by 4. 14% points.

Context-NER : Contextual Phrase Generation at Scale

1 code implementation16 Sep 2021 Himanshu Gupta, Shreyas Verma, Santosh Mashetty, Swaroop Mishra

In this paper, we introduce CONTEXT-NER, a task that aims to generate the relevant context for entities in a sentence, where the context is a phrase describing the entity but not necessarily present in the sentence.

ContextNER Language Modelling +8

Cannot find the paper you are looking for? You can Submit a new open access paper.