Generative models privatize social relations by automating social capacities into synthetic forms owned by private companies.
Cold, Calculated, and Condescending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
years
2026 5roles
background 2representative citing papers
Counterfactual prompting effects on LLMs are often indistinguishable from those caused by meaning-preserving paraphrases, causing most previously reported demographic sensitivities to disappear under proper statistical comparison.
A methodological framework detects subtle group-associated linguistic biases in LLM outputs by generating controlled synthetic minimal pairs, abstracting n-grams, and ranking high-signal fragments with a PMI variant for expert review.
AI accuracy evaluation requires four normative choices on metrics, balancing, representative data, and thresholds that embed assumptions about risks and trade-offs, as analyzed through the EU AI Act.
A literature review concludes that pursuing consensus in data annotation creates biased AI by dismissing subjective disagreements and enforcing geographic hegemony, and proposes mapping diversity instead.
citing papers explorer
-
Compared to What? Baselines and Metrics for Counterfactual Prompting
Counterfactual prompting effects on LLMs are often indistinguishable from those caused by meaning-preserving paraphrases, causing most previously reported demographic sensitivities to disappear under proper statistical comparison.