研究新闻偏见与攻击性评论的互动，比较人与大模型生成反言论的效果。
Counterspeech for Mitigating the Influence of Media Bias: Comparing Human and LLM-Generated Responses
- 构建新闻偏见、攻击评论与反言论的标注数据集
- 70%以上攻击评论强化偏见内容，凸显反言论必要性
- 优化大模型生成反言论，提升多样性与相关性
新闻偏见加剧社会分裂，常被敌意评论强化，构成传播中的关键但被忽视问题。本研究发现，超过70%的攻击性评论支持偏见文章，进一步放大偏见，对特定群体造成伤害。反言论是一种在不违反言论自由的前提下遏制有害言论的有效方法。我们首次探索新闻语境下的反言论生成，构建了包含媒体偏见、攻击性评论与反言论的标注数据集。分析显示，70%以上的攻击性评论支持偏见内容，凸显反言论的重要性。对比人类与大语言模型生成的反言论，发现模型生成内容更礼貌但缺乏新颖性和多样性。通过少量样本学习和融合新闻背景信息，我们提升了生成反言论的多样性和相关性。
原文摘要 · Abstract (English)
Biased news contributes to societal polarization and is often reinforced by hostile reader comments, constituting a vital yet often overlooked aspect of news dissemination. Our study reveals that offensive comments support biased content, amplifying bias and causing harm to targeted groups or individuals. Counterspeech is an effective approach to counter such harmful speech without violating freedom of speech, helping to limit the spread of bias. To the best of our knowledge, this is the first study to explore counterspeech generation in the context of news articles. We introduce a manually annotated dataset linking media bias, offensive comments, and counterspeech. We conduct a detailed analysis showing that over 70\% offensive comments support biased articles, amplifying bias and thus highlighting the importance of counterspeech generation. Comparing counterspeech generated by humans and large language models, we find model-generated responses are more polite but lack the novelty and diversity. Finally, we improve generated counterspeech through few-shot learning and integration of news background information, enhancing both diversity and relevance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。