LLMs exhibit higher perplexity on far-right and nationalist party texts than social-democratic ones, consistent across models and languages with correlation to translation metrics.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Behavioral audit finds emergent, city-dependent racial steering in LLM housing recommendations that changes with user identity and preference context.
citing papers explorer
-
Large Language Models are Perplexed by some Political Parties
LLMs exhibit higher perplexity on far-right and nationalist party texts than social-democratic ones, consistent across models and languages with correlation to translation metrics.
-
The Geography of Algorithmic Judgment: LLM Intermediaries, Place Identity, and Racial Steering in Housing Search
Behavioral audit finds emergent, city-dependent racial steering in LLM housing recommendations that changes with user identity and preference context.