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


Abstract
Counterspeech, defined as a response to mitigate online hate speech, is increasingly used as a non-censorial solution. The effectiveness of addressing hate speech involves dispelling the stereotypes, prejudices, and biases often subtly implied in brief, single-sentence statements or abuses. These 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 statements. The first two phases of CoARL involve sequential multi-instruction tuning, teaching the model to understand intents, reactions, and harms of offensive statements, and then learning task-specific low-rank adapter weights for generating intent-conditioned counterspeech. The final phase uses reinforcement learning to fine-tune outputs for effectiveness and nontoxicity. CoARL outperforms existing benchmarks in intent-conditioned counterspeech generation, showing an average improvement of ∼3 points in intent-conformity and ∼4 points in argument-quality metrics. Extensive human evaluation supports CoARL’s efficacy in generating superior and more context-appropriate responses compared to existing systems, including prominent LLMs like ChatGPT.
Anthology ID:
2024.naacl-long.374
Volume:
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6716–6733
Language:
URL:
https://aclanthology.org/2024.naacl-long.374
DOI:
Bibkey:
Cite (ACL):
Amey Hengle, Aswini Padhi, Sahajpreet Singh, Anil Bandhakavi, Md Shad Akhtar, and Tanmoy Chakraborty. 2024. Intent-conditioned and Non-toxic Counterspeech Generation using Multi-Task Instruction Tuning with RLAIF. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 6716–6733, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Intent-conditioned and Non-toxic Counterspeech Generation using Multi-Task Instruction Tuning with RLAIF (Hengle et al., NAACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.naacl-long.374.pdf
Copyright:
 2024.naacl-long.374.copyright.pdf