← Search

Avik Dutta

2 accepted papers

2024

Context Matters: Pushing the Boundaries of Open-Ended Answer Generation with Graph-Structured Knowledge Context

EMNLP 2024industry

This paper introduces a novel framework that combines graph-driven context retrieval in conjunction to knowledge graphs based enhancement, honing the proficiency of LLMs, especially in domain specific community question answering platforms like AskUbuntu, Unix, and ServerFault. We conduct experiment…

Cited by 4SourcePDFScholar
2024

RAR: Retrieval-augmented retrieval for code generation in low resource languages

EMNLP 2024main

Language models struggle in generating code for low-resource programming languages, since these are underrepresented in training data. Either examples or documentation are commonly used for improved code generation. We propose to use both types of information together and present retrieval augmented…