Correcting misinformation on social media with a large language model

arXiv:2403.11169v1 Announce Type: new
Abstract: Misinformation undermines public trust in science and democracy, particularly on social media where inaccuracies can spread rapidly. Experts and laypeople have shown to be effective in correcting misinformation by manually identifying and explaining inaccuracies. Nevertheless, this approach is difficult to scale, a concern as technologies like large language models (LLMs) make misinformation easier to produce. LLMs also have versatile capabilities that could accelerate misinformation correction; however, they struggle due to a lack of recent information, …

abstract arxiv cs.ai cs.cl democracy experts language language model large language large language model media misinformation public scale science social social media technologies trust type