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

Amey Hengle, Aswini Padhi, Sahajpreet Singh, Anil Bandhakavi, Md. Shad Akhtar, Tanmoy Chakraborty 0002. Intent-conditioned and Non-toxic Counterspeech Generation using Multi-Task Instruction Tuning with RLAIF. In Kevin Duh, Helena Gómez-Adorno, Steven Bethard, editors, Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), NAACL 2024, Mexico City, Mexico, June 16-21, 2024. pages 6716-6733, Association for Computational Linguistics, 2024. [doi]

Authors

Amey Hengle

This author has not been identified. Look up 'Amey Hengle' in Google

Aswini Padhi

This author has not been identified. Look up 'Aswini Padhi' in Google

Sahajpreet Singh

This author has not been identified. Look up 'Sahajpreet Singh' in Google

Anil Bandhakavi

This author has not been identified. Look up 'Anil Bandhakavi' in Google

Md. Shad Akhtar

This author has not been identified. Look up 'Md. Shad Akhtar' in Google

Tanmoy Chakraborty 0002

This author has not been identified. Look up 'Tanmoy Chakraborty 0002' in Google