From Documents to Dialogue: Building KG-RAG Enhanced AI Assistants

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Mukherjee, Manisha, Kim, Sungchul, Chen, Xiang, Luo, Dan, Yu, Tong, Mai, Tung
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915164781019136
author Mukherjee, Manisha
Kim, Sungchul
Chen, Xiang
Luo, Dan
Yu, Tong
Mai, Tung
author_facet Mukherjee, Manisha
Kim, Sungchul
Chen, Xiang
Luo, Dan
Yu, Tong
Mai, Tung
contents The Adobe Experience Platform AI Assistant is a conversational tool that enables organizations to interact seamlessly with proprietary enterprise data through a chatbot. However, due to access restrictions, Large Language Models (LLMs) cannot retrieve these internal documents, limiting their ability to generate accurate zero-shot responses. To overcome this limitation, we use a Retrieval-Augmented Generation (RAG) framework powered by a Knowledge Graph (KG) to retrieve relevant information from external knowledge sources, enabling LLMs to answer questions over private or previously unseen document collections. In this paper, we propose a novel approach for building a high-quality, low-noise KG. We apply several techniques, including incremental entity resolution using seed concepts, similarity-based filtering to deduplicate entries, assigning confidence scores to entity-relation pairs to filter for high-confidence pairs, and linking facts to source documents for provenance. Our KG-RAG system retrieves relevant tuples, which are added to the user prompts context before being sent to the LLM generating the response. Our evaluation demonstrates that this approach significantly enhances response relevance, reducing irrelevant answers by over 50% and increasing fully relevant answers by 88% compared to the existing production system.
format Preprint
id arxiv_https___arxiv_org_abs_2502_15237
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle From Documents to Dialogue: Building KG-RAG Enhanced AI Assistants
Mukherjee, Manisha
Kim, Sungchul
Chen, Xiang
Luo, Dan
Yu, Tong
Mai, Tung
Information Retrieval
The Adobe Experience Platform AI Assistant is a conversational tool that enables organizations to interact seamlessly with proprietary enterprise data through a chatbot. However, due to access restrictions, Large Language Models (LLMs) cannot retrieve these internal documents, limiting their ability to generate accurate zero-shot responses. To overcome this limitation, we use a Retrieval-Augmented Generation (RAG) framework powered by a Knowledge Graph (KG) to retrieve relevant information from external knowledge sources, enabling LLMs to answer questions over private or previously unseen document collections. In this paper, we propose a novel approach for building a high-quality, low-noise KG. We apply several techniques, including incremental entity resolution using seed concepts, similarity-based filtering to deduplicate entries, assigning confidence scores to entity-relation pairs to filter for high-confidence pairs, and linking facts to source documents for provenance. Our KG-RAG system retrieves relevant tuples, which are added to the user prompts context before being sent to the LLM generating the response. Our evaluation demonstrates that this approach significantly enhances response relevance, reducing irrelevant answers by over 50% and increasing fully relevant answers by 88% compared to the existing production system.
title From Documents to Dialogue: Building KG-RAG Enhanced AI Assistants
topic Information Retrieval
url https://arxiv.org/abs/2502.15237