Pith. sign in

REVIEW 5 cited by

Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2305.18189 v1 pith:TI6HHS5G submitted 2023-05-29 cs.CL cs.AIcs.CY

Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Models

classification cs.CL cs.AIcs.CY
keywords personasgroupslanguagemarkedstereotypesportrayalsunmarkeddemographic
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

To recognize and mitigate harms from large language models (LLMs), we need to understand the prevalence and nuances of stereotypes in LLM outputs. Toward this end, we present Marked Personas, a prompt-based method to measure stereotypes in LLMs for intersectional demographic groups without any lexicon or data labeling. Grounded in the sociolinguistic concept of markedness (which characterizes explicitly linguistically marked categories versus unmarked defaults), our proposed method is twofold: 1) prompting an LLM to generate personas, i.e., natural language descriptions, of the target demographic group alongside personas of unmarked, default groups; 2) identifying the words that significantly distinguish personas of the target group from corresponding unmarked ones. We find that the portrayals generated by GPT-3.5 and GPT-4 contain higher rates of racial stereotypes than human-written portrayals using the same prompts. The words distinguishing personas of marked (non-white, non-male) groups reflect patterns of othering and exoticizing these demographics. An intersectional lens further reveals tropes that dominate portrayals of marginalized groups, such as tropicalism and the hypersexualization of minoritized women. These representational harms have concerning implications for downstream applications like story generation.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Fair outputs, Biased Internals: Causal Potency and Asymmetry of Latent Bias in LLMs for High-Stakes Decisions

    cs.AI 2026-05 unverdicted novelty 7.0

    Open-weight LLMs show no output bias on matched mortgage applications differing only by racially-associated names, yet retain and amplify demographic representations that steering interventions can causally activate t...

  2. Persona Non Grata: LLM Persona-Driven Generations in MCQA are Unstable in Distinct Dimensions

    cs.CL 2026-07 unverdicted novelty 6.0

    Persona-driven generations by LLMs in MCQA tasks exhibit instability that differs systematically by model family, size, domain, and prompt format.

  3. The Granularity Axis: A Micro-to-Macro Latent Direction for Social Roles in Language Models

    cs.AI 2026-05 unverdicted novelty 6.0

    LLMs organize prompted social roles along a dominant, stable, and causally steerable granularity axis in representation space that runs from micro to macro levels.

  4. Whose Story Gets Told? Positionality and Bias in LLM Summaries of Life Narratives

    cs.CL 2026-04 unverdicted novelty 6.0

    A proposed pipeline shows LLMs introduce detectable race and gender biases when summarizing life narratives, creating potential for representational harm in research.

  5. What if AI systems weren't chatbots?

    cs.CY 2026-05 unverdicted novelty 3.0

    Chatbot AI systems often fail complex needs while projecting authority, contributing to deskilling, labor displacement, economic concentration, and high environmental costs, so alternative pluralistic and task-specifi...