情境化反言论:适应、个性化与评估策略
Contextualized Counterspeech: Strategies for Adaptation, Personalization, and Evaluation
AI总结:
本文提出并评估了基于LLaMA2-13B的情境化与个性化反言论生成策略,通过定量指标和众包人工评估证明其显著优于通用反言论,并揭示人工与算法评估存在分歧,强调内容审核需加强人机协作。
摘要:
AI生成的反言论通过直接回复促进文明对话,为遏制网络毒性提供了一种有前景且可扩展的策略。然而,当前的反言论是一刀切的,缺乏对审核情境和相关用户的适应。我们提出并评估了多种生成定制化反言论的策略,使其适应审核情境并为被审核用户提供个性化。我们指导一个LLaMA2-13B模型生成反言论,并基于不同的情境信息和微调策略对各种配置进行实验。我们通过定量指标和经由预先注册的混合设计众包实验收集的人工评估相结合的方式,识别出能够生成有说服力反言论的配置。结果表明,情境化反言论在充分性和说服力方面能够显著优于最先进的通用反言论,同时不损害其他特性。我们的发现还揭示了定量指标与人工评估之间的相关性较差,表明这些方法评估的是不同方面,并凸显了对细致评估方法的需求。情境化AI生成反言论的有效性以及人工评估与算法评估之间的分歧,强调了在内容审核中加强人机协作的重要性。
英文摘要:
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 state-of-the-art generic counterspeech in adequacy and persuasiveness, without compromising other characteristics. Our findings also reveal a poor correlation between quantitative indicators and human evaluations, suggesting that these methods assess different aspects and highlighting the need for nuanced evaluation methodologies. The effectiveness of contextualized AI-generated counterspeech and the divergence between human and algorithmic evaluations underscore the importance of increased human-AI collaboration in content moderation.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。