Please use this identifier to cite or link to this item: http://repository.iiitd.edu.in/xmlui/handle/123456789/1616
Full metadata record
DC FieldValueLanguage
dc.contributor.authorAddala, Krishnasai-
dc.contributor.authorBaghel, Kabir Dev Paul-
dc.contributor.authorShah, Rajiv Ratn (Advisor)-
dc.date.accessioned2024-05-27T05:40:49Z-
dc.date.available2024-05-27T05:40:49Z-
dc.date.issued2023-11-27-
dc.identifier.urihttp://repository.iiitd.edu.in/xmlui/handle/123456789/1616-
dc.description.abstractDespite the growing capabilities of Large Language Models (LLMs) in various domains, their proficiency in addressing domain-specific high-school physics questions remains an unexplored area. In this study, we present a pioneering data set curated from NCERT exemplar solutions strategically designed to facilitate the use of LLMs to solve school physics questions. Originally comprising 766 questions accompanied by LaTeX representations, the dataset underwent a sophisticated augmentation process that expanded its scope to an impressive 7,983 questions. The augmentation employed innovative techniques which effectively broaden the dataset’s coverage. The dataset, prioritizing text-based questions, is formatted as JSON objects detailing instructions, inputs, and outputs. Post evaluation, we noted significant scores: METEOR at 0.282 and BERTScore F1 at 0.833, indicating a close alignment between generated and reference texts.en_US
dc.language.isoen_USen_US
dc.publisherIIIT-Delhien_US
dc.subjectLarge Language Modelsen_US
dc.subjectHigh School Educationen_US
dc.subjectDataseten_US
dc.subjectChain of Thoughten_US
dc.subjectArtificial Intelligenten_US
dc.titleAI based NLP systemsen_US
dc.typeOtheren_US
Appears in Collections:Year-2023

Files in This Item:
File Description SizeFormat 
AI_based_NLP_Systems_BTPReport - Kabir Dev Paul Baghel.pdf
  Restricted Access
269.87 kBAdobe PDFView/Open Request a copy


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.