Pith. sign in

REVIEW 3 cited by

Nationality Bias in Text Generation

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2302.02463 v3 pith:ULBKL7V6 submitted 2023-02-05 cs.CL cs.AI

Pranav Narayanan Venkit , Sanjana Gautam , Ruchi Panchanadikar , Ting-Hao 'Kenneth' Huang , Shomir Wilson This is my paper · ORCID
classification cs.CLcs.AI
keywords biasgpt-2modelsnationalityadversarialbiasesexploregeneration
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Little attention is placed on analyzing nationality bias in language models, especially when nationality is highly used as a factor in increasing the performance of social NLP models. This paper examines how a text generation model, GPT-2, accentuates pre-existing societal biases about country-based demonyms. We generate stories using GPT-2 for various nationalities and use sensitivity analysis to explore how the number of internet users and the country's economic status impacts the sentiment of the stories. To reduce the propagation of biases through large language models (LLM), we explore the debiasing method of adversarial triggering. Our results show that GPT-2 demonstrates significant bias against countries with lower internet users, and adversarial triggering effectively reduces the same.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

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

  1. Generating the Modal Worker: A Cross-Model Audit of Race and Gender in LLM-Generated Personas Across 41 Occupations

    cs.HC 2025-10 conditional novelty 6.0 of 10

    Four major LLMs generate occupational personas whose race and gender distributions deviate from U.S. workforce data in shared, patterned ways: White and Black workers are underrepresented while Hispanic and Asian work...

  2. McBE: A Multi-task Chinese Bias Evaluation Benchmark for Large Language Models

    cs.CL 2025-07 conditional novelty 6.0 of 10

    A new Chinese bias benchmark with 4,077 instances and five tasks indicates larger language models are less biased than smaller ones when bias is measured through understanding tasks.

  3. OrgAccess: A Benchmark for Role Based Access Control in Organization Scale LLMs

    cs.AI 2025-05 conditional novelty 6.0 of 10

    OrgAccess, a 70k-query synthetic RBAC benchmark, shows current LLMs including GPT-4.1 (F1 0.27 on the hardest split) struggle badly with permission adherence.

Pith tools