Comprehensive Comparison of RAG Methods Across Multi-Domain Conversational QA

Klejda Alushi, Jan Strich, Chris Biemann, Martin Semmann


Abstract
Conversational question answering increasingly relies on retrieval-augmented generation (RAG) to ground large language models (LLMs) in external knowledge. Yet, most existing studies evaluate RAG methods in isolation and primarily focus on single-turn settings. This paper addresses the lack of a systematic comparison of RAG methods for multi-turn conversational QA, where dialogue history, coreference, and shifting user intent substantially complicate retrieval. We present a comprehensive empirical study of vanilla and advanced RAG methods across eight diverse conversational QA datasets spanning multiple domains. Using a unified experimental setup, we evaluate retrieval quality and answer generation using generator and retrieval metrics, and analyze how performance evolves across conversation turns. Our results show that robust yet straightforward methods, such as reranking, hybrid BM25, and HyDE, consistently outperform vanilla RAG. In contrast, several advanced techniques fail to yield gains and can even degrade performance below the No-RAG baseline. We further demonstrate that dataset characteristics and dialogue length strongly influence retrieval effectiveness, explaining why no single RAG strategy dominates across settings. Overall, our findings indicate that effective conversational RAG depends less on method complexity than on alignment between the retrieval strategy and the dataset structure. We publish the code used.[GitHub Repository]
Anthology ID:
2026.eacl-srw.17
Volume:
Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 4: Student Research Workshop)
Month:
March
Year:
2026
Address:
Rabat, Morocco
Editors:
Selene Baez Santamaria, Sai Ashish Somayajula, Atsuki Yamaguchi
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
233–247
Language:
URL:
https://aclanthology.org/2026.eacl-srw.17/
DOI:
Bibkey:
Cite (ACL):
Klejda Alushi, Jan Strich, Chris Biemann, and Martin Semmann. 2026. Comprehensive Comparison of RAG Methods Across Multi-Domain Conversational QA. In Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 4: Student Research Workshop), pages 233–247, Rabat, Morocco. Association for Computational Linguistics.
Cite (Informal):
Comprehensive Comparison of RAG Methods Across Multi-Domain Conversational QA (Alushi et al., EACL 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.eacl-srw.17.pdf
Attachment:
 2026.eacl-srw.17.attachment.zip