Humanities‐in‐the‐Loop: Using Close Reading as a Method for Retrieval‐Augmented Generation ( RAG )
Proceedings of the Association for Information Science and Technology · 2025-10 · 62 (1) · 1185-1189
DOI: 10.1002/pra2.1355 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the Association for Information Science and Technology, online erschienen am 16.10.2025. Verfasst von Jing Zhou und 2 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 19 Literaturangaben.
Abstract (Originalsprache)
This paper proposes Humanities‐in‐the‐Loop, a methodological framework that embeds close reading into each stage of the Retrieval‐Augmented Generation (RAG) pipeline to enhance the processing of digital archival materials. This framework includes manual annotation, knowledge maintenance, reviewer validation, prompt engineering, and human interpretation. Taking the diaries of Coching Chu as a case study, the system addresses the limitations of conventional RAG methods in capturing the contextual complexity and historical nuance inherent in personal archives. An evaluation further confirms the effectiveness of this approach in delivering faithful, contextually grounded responses. The proposed framework not only enhances answer accuracy and interpretability but also enables traceable, human‐centered inquiry in digital humanities research.
Zitieren
APA
Zhou, J., Si, L., & Hou, W. (2025). Humanities‐in‐the‐Loop: Using Close Reading as a Method for Retrieval‐Augmented Generation ( RAG ). Proceedings of the Association for Information Science and Technology, 62(1), 1185-1189. https://doi.org/10.1002/pra2.1355
Vancouver
Zhou J, Si L, Hou W. Humanities‐in‐the‐Loop: Using Close Reading as a Method for Retrieval‐Augmented Generation ( RAG ). Proceedings of the Association for Information Science and Technology. 2025;62(1):1185-1189. doi:10.1002/pra2.1355
BibTeX
@article{Zhou2025,
author = {Zhou, Jing and Si, Li and Hou, Wenjun},
title = {Humanities‐in‐the‐Loop: Using Close Reading as a Method for Retrieval‐Augmented Generation ( RAG )},
journal = {Proceedings of the Association for Information Science and Technology},
year = {2025},
volume = {62},
number = {1},
pages = {1185--1189},
doi = {10.1002/pra2.1355}
}
EUVIMED