no code implementations • 25 Mar 2024 • Lingzi Hong, Pengcheng Luo, Eduardo Blanco, Xiaoying Song
We first explore methods that utilize large language models (LLM) to generate counterspeech constrained by potential conversation outcomes.
no code implementations • 8 Dec 2023 • Xinchen Yu, Eduardo Blanco, Lingzi Hong
A linguistic analysis uncovers the differences in the language of replies that elicit follow-up conversations with high and low incivility.
1 code implementation • NAACL 2022 • Xinchen Yu, Eduardo Blanco, Lingzi Hong
Hate speech is plaguing the cyberspace along with user-generated content.