Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Shojaee, Parshin, Harsha, Sai Sree, Luo, Dan, Maharaj, Akash, Yu, Tong, Li, Yunyao
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2501.14998
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916582040535040
author Shojaee, Parshin
Harsha, Sai Sree
Luo, Dan
Maharaj, Akash
Yu, Tong
Li, Yunyao
author_facet Shojaee, Parshin
Harsha, Sai Sree
Luo, Dan
Maharaj, Akash
Yu, Tong
Li, Yunyao
contents Recent advancements in Large Language Models and Retrieval-Augmented Generation have boosted interest in domain-specific question-answering for enterprise products. However, AI Assistants often face challenges in multi-product QA settings, requiring accurate responses across diverse domains. Existing multi-domain RAG-QA approaches either query all domains indiscriminately, increasing computational costs and LLM hallucinations, or rely on rigid resource selection, which can limit search results. We introduce MKP-QA, a novel multi-product knowledge-augmented QA framework with probabilistic federated search across domains and relevant knowledge. This method enhances multi-domain search quality by aggregating query-domain and query-passage probabilistic relevance. To address the lack of suitable benchmarks for multi-product QAs, we also present new datasets focused on three Adobe products: Adobe Experience Platform, Target, and Customer Journey Analytics. Our experiments show that MKP-QA significantly boosts multi-product RAG-QA performance in terms of both retrieval accuracy and response quality.
format Preprint
id arxiv_https___arxiv_org_abs_2501_14998
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Federated Retrieval Augmented Generation for Multi-Product Question Answering
Shojaee, Parshin
Harsha, Sai Sree
Luo, Dan
Maharaj, Akash
Yu, Tong
Li, Yunyao
Computation and Language
Recent advancements in Large Language Models and Retrieval-Augmented Generation have boosted interest in domain-specific question-answering for enterprise products. However, AI Assistants often face challenges in multi-product QA settings, requiring accurate responses across diverse domains. Existing multi-domain RAG-QA approaches either query all domains indiscriminately, increasing computational costs and LLM hallucinations, or rely on rigid resource selection, which can limit search results. We introduce MKP-QA, a novel multi-product knowledge-augmented QA framework with probabilistic federated search across domains and relevant knowledge. This method enhances multi-domain search quality by aggregating query-domain and query-passage probabilistic relevance. To address the lack of suitable benchmarks for multi-product QAs, we also present new datasets focused on three Adobe products: Adobe Experience Platform, Target, and Customer Journey Analytics. Our experiments show that MKP-QA significantly boosts multi-product RAG-QA performance in terms of both retrieval accuracy and response quality.
title Federated Retrieval Augmented Generation for Multi-Product Question Answering
topic Computation and Language
url https://arxiv.org/abs/2501.14998