Federated Retrieval Augmented Generation for Multi-Product Question Answering

Parshin Shojaee, Sai Sree Harsha, Dan Luo, Akash Maharaj, Tong Yu, Yunyao Li


Abstract
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.
Anthology ID:
2025.coling-industry.33
Volume:
Proceedings of the 31st International Conference on Computational Linguistics: Industry Track
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Owen Rambow, Leo Wanner, Marianna Apidianaki, Hend Al-Khalifa, Barbara Di Eugenio, Steven Schockaert, Kareem Darwish, Apoorv Agarwal
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
387–397
Language:
URL:
https://aclanthology.org/2025.coling-industry.33/
DOI:
Bibkey:
Cite (ACL):
Parshin Shojaee, Sai Sree Harsha, Dan Luo, Akash Maharaj, Tong Yu, and Yunyao Li. 2025. Federated Retrieval Augmented Generation for Multi-Product Question Answering. In Proceedings of the 31st International Conference on Computational Linguistics: Industry Track, pages 387–397, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
Federated Retrieval Augmented Generation for Multi-Product Question Answering (Shojaee et al., COLING 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.coling-industry.33.pdf