EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Improving the Domain Adaptation of Retrieval Augmented Generation (RAG) Models for Open Domain Question Answering

Shamane Siriwardhana, Rivindu Weerasekera, Elliott Wen, Tharindu Kaluarachchi, Rajib Rana, Suranga Nanayakkara

Transactions of the Association for Computational Linguistics · 12.01.2023 · 11 · 1-17

DOI: 10.1162/tacl_a_00530 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Transactions of the Association for Computational Linguistics, online erschienen am 12.01.2023. Verfasst von Shamane Siriwardhana und 5 weiteren Autor:innen. Die Arbeit wurde bisher 342-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Retrieval Augment Generation (RAG) is a recent advancement in Open-Domain Question Answering (ODQA). RAG has only been trained and explored with a Wikipedia-based external knowledge base and is not optimized for use in other specialized domains such as healthcare and news. In this paper, we evaluate the impact of joint training of the retriever and generator components of RAG for the task of domain adaptation in ODQA. We propose RAG-end2end, an extension to RAG that can adapt to a domain-specific knowledge base by updating all components of the external knowledge base during training. In addition, we introduce an auxiliary training signal to inject more domain-specific knowledge. This auxiliary signal forces RAG-end2end to reconstruct a given sentence by accessing the relevant information from the external knowledge base. Our novel contribution is that, unlike RAG, RAG-end2end does joint training of the retriever and generator for the end QA task and domain adaptation. We evaluate our approach with datasets from three domains: COVID-19, News, and Conversations, and achieve significant performance improvements compared to the original RAG model. Our work has been open-sourced through the HuggingFace Transformers library, attesting to our work’s credibility and technical consistency.

Zitieren

APA

Siriwardhana, S., Weerasekera, R., Wen, E., Kaluarachchi, T., Rana, R., & Nanayakkara, S. (2023). Improving the Domain Adaptation of Retrieval Augmented Generation (RAG) Models for Open Domain Question Answering. Transactions of the Association for Computational Linguistics, 11, 1-17. https://doi.org/10.1162/tacl_a_00530

Vancouver

Siriwardhana S, Weerasekera R, Wen E, Kaluarachchi T, Rana R, Nanayakkara S. Improving the Domain Adaptation of Retrieval Augmented Generation (RAG) Models for Open Domain Question Answering. Transactions of the Association for Computational Linguistics. 2023;11:1-17. doi:10.1162/tacl_a_00530

BibTeX
@article{Siriwardhana2023,
  author = {Siriwardhana, Shamane and Weerasekera, Rivindu and Wen, Elliott and Kaluarachchi, Tharindu and Rana, Rajib and Nanayakkara, Suranga},
  title = {Improving the Domain Adaptation of Retrieval Augmented Generation (RAG) Models for Open Domain Question Answering},
  journal = {Transactions of the Association for Computational Linguistics},
  year = {2023},
  volume = {11},
  pages = {1--17},
  doi = {10.1162/tacl_a_00530}
}
Kostenlos starten →