Intent-conditioned and Non-toxic Counterspeech Generation using Multi-Task Instruction Tuning with RLAIF

arXiv:2403.10088v1 Announce Type: new
Abstract: Counterspeech, defined as a response to mitigate online hate speech, is increasingly used as a non-censorial solution. Addressing hate speech effectively involves dispelling the stereotypes, prejudices, and biases often subtly implied in brief, single-sentence statements or abuses. These implicit expressions challenge language models, especially in seq2seq tasks, as model performance typically excels with longer contexts. Our study introduces CoARL, a novel framework enhancing counterspeech generation by modeling the pragmatic implications underlying social biases in hateful …

abstract arxiv biases challenge cs.ai cs.cl hate speech language language models rlaif solution speech stereotypes type