Contextualized Counterspeech: Strategies for Adaptation, Personalization, and Evaluation
Lorenzo Cima, Alessio Miaschi, Amaury Trujillo, Marco Avvenuti, Felice, Dell'Orletta, Stefano Cresci

TL;DR
This paper develops and evaluates strategies for generating personalized, context-aware counterspeech using LLaMA2-13B, demonstrating improved persuasiveness over generic methods and highlighting evaluation challenges.
Contribution
It introduces tailored counterspeech generation methods that adapt to moderation context and user, advancing beyond one-size-fits-all approaches.
Findings
Contextualized counterspeech outperforms generic in persuasiveness
Quantitative indicators poorly correlate with human judgments
Human-AI collaboration is crucial for effective moderation
Abstract
AI-generated counterspeech offers a promising and scalable strategy to curb online toxicity through direct replies that promote civil discourse. However, current counterspeech is one-size-fits-all, lacking adaptation to the moderation context and the users involved. We propose and evaluate multiple strategies for generating tailored counterspeech that is adapted to the moderation context and personalized for the moderated user. We instruct an LLaMA2-13B model to generate counterspeech, experimenting with various configurations based on different contextual information and fine-tuning strategies. We identify the configurations that generate persuasive counterspeech through a combination of quantitative indicators and human evaluations collected via a pre-registered mixed-design crowdsourcing experiment. Results show that contextualized counterspeech can significantly outperform…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
- 🤗alemiaschi/LLaMA-2-13b-chat_CounterSpeech_Mumodel· 5 dl5 dl
- 🤗alemiaschi/LLaMA-2-13b-chat_CounterSpeech_MuRemodel· 6 dl6 dl
- 🤗alemiaschi/LLaMA-2-13b-chat_CounterSpeech_MuHsRemodel· 2 dl2 dl
- 🤗alemiaschi/LLaMA-2-13b-chat_CounterSpeech_Hsmodel· 1 dl1 dl
- 🤗alemiaschi/LLaMA-2-13b-chat_CounterSpeech_MuHsmodel· 2 dl2 dl
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsHate Speech and Cyberbullying Detection · Misinformation and Its Impacts · Spam and Phishing Detection
