Using Large Language Models for Qualitative Analysis can Introduce Serious Bias (English)

Large Language Models (LLMs) are quickly becoming ubiquitous, but the implications for social science research are not yet well understood. This paper asks whether LLMs can help us analyse large-N qualitative data from open-ended interviews, with an application to transcripts of interviews with displaced Rohingya people in Cox’s Bazaar, Bangladesh. The analysis finds that a great deal of caution is needed in using LLMs to annotate text as there is...

DETAILS

Author

Ashwin,Julian;

Chhabra,Aditya;

Rao,Vijayendra;
Document Date
2023/11/07
Document Type
Policy Research Working Paper
Report Number
WPS10597
Volume No
1
Country
World,
Region
Other,
Disclosure Date
2023/11/07
Disclosure Status
Disclosed
Doc Name
Using Large Language Models for Qualitative Analysis can Introduce Serious Bias

DOWNLOADS

COMPLETE REPORT

Official version of document (may contain signatures, etc)

Official PDF
TXT*
Total Downloads** : 1378
Download Stats
*The text version is uncorrected OCR text and is included solely to benefit users with slow connectivity.

Citation

Ashwin,Julian; Chhabra,Aditya; Rao,Vijayendra.

Using Large Language Models for Qualitative Analysis can Introduce Serious Bias (English). Policy Research working paper ; no. WPS 10597; Paper is funded by the Knowledge for Change Program (KCP) Washington, D.C. : World Bank Group. http://documents.worldbank.org/curated/en/099433311072326082

Using Large Language Models for Qualitative Analysis can Introduce Serious Bias (English)

DETAILS

DOWNLOADS

COMPLETE REPORT

Citation

RELATED LINKS

SUBSCRIBE TO EMAIL ALERTS