Zero-shot LLM-generated counterspeech to conspiracy theories is shallow, repetitive, and about 10% confabulated, with no model reaching practical effectiveness.
Empathy-based counterspeech can reduce racist hate speech in a social media field experiment.Proceed- ings of the National Academy of Sciences, 118(50): e2116310118, 2021
3 Pith papers cite this work, alongside 138 external citations. Polarity classification is still indexing.
3
Pith papers citing it
138
external citations · Crossref
representative citing papers
Cross-lingual analysis of 1.76M Singapore comments finds culturally specific hate targets but shared binding moral grammar and threat frames across languages.
A counterspeech bot influences bystanders subtly through credible and normative presence, with cognitive strategies paired with positive tone proving relatively effective while poor performance can discourage participation.
citing papers explorer
-
Cultural Targets, Structural Frames, Binding Morals: A Cross-Lingual Audit of Online Hate in Multicultural Singapore
Cross-lingual analysis of 1.76M Singapore comments finds culturally specific hate targets but shared binding moral grammar and threat frames across languages.