Synthetic Interlocutors. Experiments with Generative AI to Prolong Ethnographic Encounters

TL;DR

This paper explores the use of Retrieval Augmented Generation with large language models to create Synthetic Interlocutors that can prolong ethnographic encounters and facilitate new insights by re-engaging with ethnographic data.

Contribution

It introduces a novel method of using RAG-based chatbots as ethnographic interlocutors to extend and deepen ethnographic research interactions.

Findings

RAG can effectively digest ethnographic materials

Synthetic Interlocutors can prolong ethnographic encounters

They enable collaborative and serendipitous research moments

Abstract

This paper introduces "Synthetic Interlocutors" for ethnographic research. Synthetic Interlocutors are chatbots ingested with ethnographic textual material (interviews and observations) by using Retrieval Augmented Generation (RAG). We integrated an open-source large language model with ethnographic data from three projects to explore two questions: Can RAG digest ethnographic material and act as ethnographic interlocutor? And, if so, can Synthetic Interlocutors prolong encounters with the field and extend our analysis? Through reflections on the process of building our Synthetic Interlocutors and an experimental collaborative workshop, we suggest that RAG can digest ethnographic materials, and it might lead to prolonged, yet uneasy ethnographic encounters that allowed us to partially recreate and re-visit fieldwork interactions while facilitating opportunities for novel analytic insights. Synthetic Interlocutors can produce collaborative, ambiguous and serendipitous moments.