24 citations · 24 across the 5 of their papers we have counts for
Showing 2025Show all
3 papers · 1 filter
cs.AI2025
Linear socio-demographic representations emerge in Large Language Models from indirect cues
Paul Bouchaud, Pedro Ramaciotti
We investigate how LLMs encode sociodemographic attributes of human conversational partners inferred from indirect cues such as names and occupations. We show that LLMs develop lin…
cs.SI2025
Web Crawler Restrictions, AI Training Datasets \& Political Biases
Paul Bouchaud, Pedro Ramaciotti
Large language models rely on web-scraped text for training; concurrently, content creators are increasingly blocking AI crawlers to retain control over their data. We analyze craw…
cs.SI2025
Community Notes undermoderate polarizing content by design creating risks in electoral processes
Paul Bouchaud, Pedro Ramaciotti
Community Notes (CNs) of X enables users to collaboratively moderate misleading content. To resolve conflicting moderation, CNs infers a latent ideological dimension and selects no…