Mitigating Toxic Degeneration with Empathetic Data: Exploring the Relationship Between Toxicity and Empathy

Allison Lahnala, Charles Welch, Béla Neuendorf, Lucie Flek


Abstract
Large pre-trained neural language models have supported the effectiveness of many NLP tasks, yet are still prone to generating toxic language hindering the safety of their use. Using empathetic data, we improve over recent work on controllable text generation that aims to reduce the toxicity of generated text. We find we are able to dramatically reduce the size of fine-tuning data to 7.5-30k samples while at the same time making significant improvements over state-of-the-art toxicity mitigation of up to 3.4% absolute reduction (26% relative) from the original work on 2.3m samples, by strategically sampling data based on empathy scores. We observe that the degree of improvements is subject to specific communication components of empathy. In particular, the more cognitive components of empathy significantly beat the original dataset in almost all experiments, while emotional empathy was tied to less improvement and even underperforming random samples of the original data. This is a particularly implicative insight for NLP work concerning empathy as until recently the research and resources built for it have exclusively considered empathy as an emotional concept.
Anthology ID:
2022.naacl-main.363
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
July
Year:
2022
Address:
Seattle, United States
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4926–4938
Language:
URL:
https://aclanthology.org/2022.naacl-main.363
DOI:
10.18653/v1/2022.naacl-main.363
Bibkey:
Cite (ACL):
Allison Lahnala, Charles Welch, Béla Neuendorf, and Lucie Flek. 2022. Mitigating Toxic Degeneration with Empathetic Data: Exploring the Relationship Between Toxicity and Empathy. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4926–4938, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Mitigating Toxic Degeneration with Empathetic Data: Exploring the Relationship Between Toxicity and Empathy (Lahnala et al., NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-main.363.pdf