Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
Unfair and Unsafe: Everyday Bias Triggers Emergent Misalignment
Alex Martí Guiu, Nicolas Zumarraga, Kevin O'Sullivan +2
Emergent misalignment (EM) occurs when fine-tuning a language model to a narrow task makes it misaligned on unrelated ones. Because organizations now routinely fine-tune models on…
cs.CL2026
Polistemics: Evaluating LLMs as Information Mediators in Politics & Elections
Baran Peters, Gabor Hollbeck, Robert Jakob +1
As LLMs increasingly shape the political information citizens rely on, no standard exists to assess whether they do so responsibly. We introduce Polistemics, a theory-grounded diag…