Humanities‐in‐the‐Loop: Using Close Reading as a Method for Retrieval‐Augmented Generation (RAG)
Abstract
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.
Read the paper
Related studies
- Knowledge Management Perspective of Generative Artificial Intelligence
- Navigating Generative Artificial Intelligence Promises and Perils for Knowledge and Creative Work
- Characterizing the evolving research on enterprise content management
- Large language models and multimodal foundation models for precision oncology
- From Generative AI to Extended Reality: Multidisciplinary Perspectives on the Challenges, Opportunities, and Future of Educational Computing
- Generative Artificial Intelligence: A New Engine for Advancing Environmental Science and Engineering
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.