Counterspeech for Mitigating the Influence of Media Bias: Comparing Human and LLM-Generated Responses
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 24 of its 48 references that are in the map. First posted on arXiv 20 Aug 2025.
Builds on
24 of 48 references.
References · 24
- 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
- 2016Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translationcited by 1,475
- 2015A Diversity-Promoting Objective Function for Neural Conversation Modelscited by 1,077
- 2020HateXplain: A Benchmark Dataset for Explainable Hate Speech Detectioncited by 407
- 2023From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Modelscited by 260
- 2019A Benchmark Dataset for Learning to Intervene in Online Hate Speechcited by 129
- 2020We Can Detect Your Bias: Predicting the Political Ideology of News Articlescited by 92
- 2019In Plain Sight: Media Bias Through the Lens of Factual Reportingcited by 68
- 2018Thou shalt not hate: Countering Online Hate Speechcited by 64
- 2018Cross-topic Argument Mining from Heterogeneous Sources Using Attention-based Neural Networkscited by 58
- 2022Neural Media Bias Detection Using Distant Supervision With BABE -- Bias Annotations By Expertscited by 56
- 2024Investigating Bias in LLM-Based Bias Detection: Disparities between LLMs and Human Perceptioncited by 56
12 more
- 2018Generating More Interesting Responses in Neural Conversation Models with Distributional Constraintscited by 33
- 2020Analyzing Political Bias and Unfairness in News Articles at Different Levels of Granularitycited by 32
- 2022Hate Speech and Counter Speech Detection: Conversational Context Does Mattercited by 32
- 2024On the Relationship between Truth and Political Bias in Language Modelscited by 31
- 2020The Role of the Crowd in Countering Misinformation: A Case Study of the COVID-19 Infodemiccited by 24
- 2018The Effect of Extremist Violence on Hateful Speech Onlinecited by 17
- 2024On Zero-Shot Counterspeech Generation by LLMscited by 17
- 2020Context in Informational Bias Detectioncited by 15
- 2021HateBR: A Large Expert Annotated Corpus of Brazilian Instagram Comments for Offensive Language and Hate Speech Detectioncited by 15
- 2024IndiVec: An Exploration of Leveraging Large Language Models for Media Bias Detection with Fine-Grained Bias Indicatorscited by 15
- 2024CrowdCounter: A benchmark type-specific multi-target counterspeech datasetcited by 5
- 2023Data-Augmented and Retrieval-Augmented Context Enrichment in Chinese Media Bias Detectioncited by 2
Built on by
Not cited yet.