Can Language Model Moderators Improve the Health of Online Discourse?

arXiv:2311.10781v2 Announce Type: replace
Abstract: Conversational moderation of online communities is crucial to maintaining civility for a constructive environment, but it is challenging to scale and harmful to moderators. The inclusion of sophisticated natural language generation modules as a force multiplier to aid human moderators is a tantalizing prospect, but adequate evaluation approaches have so far been elusive. In this paper, we establish a systematic definition of conversational moderation effectiveness grounded on moderation literature and establish design criteria for conducting …

abstract arxiv communities conversational cs.ai cs.cl discourse environment health human inclusion language language generation language model moderation moderators modules natural natural language natural language generation online communities scale type