Pith. sign in

REVIEW 4 cited by

Probing Pre-Trained Language Models for Cross-Cultural Differences in Values

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 2203.13722 v3 pith:Q4JMSS52 submitted 2022-03-25 cs.CL

classification cs.CL
keywords modelsvaluesacrosscross-culturalcultureslanguageptlmssurveys
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Language embeds information about social, cultural, and political values people hold. Prior work has explored social and potentially harmful biases encoded in Pre-Trained Language models (PTLMs). However, there has been no systematic study investigating how values embedded in these models vary across cultures. In this paper, we introduce probes to study which values across cultures are embedded in these models, and whether they align with existing theories and cross-cultural value surveys. We find that PTLMs capture differences in values across cultures, but those only weakly align with established value surveys. We discuss implications of using mis-aligned models in cross-cultural settings, as well as ways of aligning PTLMs with value surveys.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

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

  1. Toward Socially Aware Vision-Language Models: Evaluating Cultural Competence Through Multimodal Story Generation

    cs.CL 2025-08 conditional novelty 6.0 of 10

    An evaluation of five VLMs on culturally-prompted multimodal story generation finds measurable cultural adaptation alongside metric bias and inverse alignment in some models.

  2. A Dual-Layered Evaluation of Geopolitical and Cultural Bias in LLMs

    cs.CL 2025-06 conditional novelty 6.0 of 10

    A multilingual two-phase evaluation shows LLMs lean on query language for factual questions and on training-country perspective for territorial and historical disputes.

  3. Prompt Programming for Cultural Bias and Alignment of Large Language Models

    cs.AI 2026-03 conditional novelty 5.0 of 10

    Automatically optimized prompts (DSPy) reduce survey-measured cultural distance for open-weight LLMs more often than manual cultural prompting, with MIPROv2 and a large proposer model giving the most consistent gains.

  4. Do Large Language Models Understand Morality Across Cultures?

    cs.CL 2025-07 reject novelty 4.0 of 10

    Small language models compress cross-cultural moral differences, producing more uniformly permissive and less varied judgments than international survey data.

Pith tools