Zum Inhalt springen

Nur-Lesen-Fassung: Das Forschungsinformationssystem (FIS) ist aus Sicherheitsgründen vorübergehend durch diese Nur-Lesen-Fassung ersetzt. Alle öffentlichen Inhalte und Volltexte sind weiterhin abrufbar; Anmeldung, Bearbeitung, Einreichung und Statistiken stehen nicht zur Verfügung. Bei Fragen: fis@uni-bamberg.de

Start › Publikationen › Which Demographics do LLMs Default to During Annotation?

Publikation

Which Demographics do LLMs Default to During Annotation?

Schäfer, Johannes; Combs, Aidan; Bagdon, Christopher Doyle; u. a. (2026): Which Demographics do LLMs Default to During Annotation?, in: Bamberg: Otto-Friedrich-Universität, S. 17331–17348.

Details

Fakultät/Lehrstuhl
Autorin(nen)/Autor(en)
Schäfer, Johannes; Combs, Aidan; Bagdon, Christopher Doyle; Li, Jiahui; ORCID iDProbol, Nadine; Greschner, Lynn; ORCID iDPapay, Sean; Menchaca Resendiz, Yarik; Velutharambath, Aswathy; Wuehrl, Amelie; ORCID iDWeber, Sabine; ORCID iDKlinger, Roman
Verlagsangabe
Otto-Friedrich-Universität : Bamberg
Erscheinungsjahr
2026
Quelle/Weitere Ausgabe
Wanxiang Che, Joyce Nabende, Ekaterina Shutova, u. a. (Hrsg.), Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics, Association for Computational Linguistics, 2025, S. 17331–17348, ISBN: 979-8-89176-251-0
Jahr der Erstpublikation
2025
Sprache(n)
Englisch
Lizenz
URN
Abstract

Demographics and cultural background of annotators influence the labels they assign in text annotation – for instance, an elderly woman might find it offensive to read a message addressed to a “bro”, but a male teenager might find it appropriate. It is therefore important to acknowledge label variations to not underrepresent members of a society. Two research directions developed out of this observation in the context of using large language models (LLM) for data annotations, namely (1) studying biases and inherent knowledge of LLMs and (2) injecting diversity in the output by manipulating the prompt with demographic information. We combine these two strands of research and ask the question to which demographics an LLM resorts when no demographics is given. To answer this question, we evaluate which attributes of human annotators LLMs inherently mimic. Furthermore, we compare non-demographic conditioned prompts and placebo-conditioned prompts (e.g., “you are an annotator who lives in house number 5”) to demographics-conditioned prompts (“You are a 45 year old man and an expert on politeness annotation. How do you rate {instance}”). We study these questions for politeness and offensiveness annotations on the POPQUORN data set, a corpus created in a controlled manner to investigate human label variations based on demographics which has not been used for LLM-based analyses so far. We observe notable influences related to gender, race, and age in demographic prompting, which contrasts with previous studies that found no such effects

Freie Schlagwort(e)
-
Peer Reviewed
ja
Internationale Verbreitung
ja
Open-Access-Zeitschrift
ja
Dokumenttyp
Konferenzveröffentlichung
URI
Datum der Freischaltung
24.03.2026
Projekt(e)

Permalink: https://fis.uni-bamberg.de/handle/uniba/114413 · Daten als JSON · Zitieren: BibTeX · RIS

Datenstand: 15.11.2026

Eingeschränkter Lesezugriff: Anmeldung, Bearbeitung und Einreichung sind vorübergehend deaktiviert.