The field of misinformation detection and analysis is rapidly evolving, with a growing focus on developing innovative methods to counter the spread of fake news. A key direction in this area is the use of large language models (LLMs) and generative agents to improve the accuracy and efficiency of fact-checking and claim verification. Researchers are exploring the potential of these models to detect manipulated content, identify zero-day manipulated content, and retrieve previously fact-checked claims. Additionally, there is a growing interest in understanding the impact of LLM-generated fake news on news ecosystems and developing methods to mitigate its effects. Noteworthy papers in this area include:

• A study on the application and optimization of large models based on prompt tuning for fact-check-worthiness estimation, which demonstrates the effectiveness of this method in improving the accuracy of fact-checking.
• Research on the potential of generative agents in crowdsourced fact-checking, which shows that these agents can outperform human crowds in truthfulness classification and exhibit higher internal consistency.
• A paper on detecting manipulated contents using knowledge-grounded inference, which proposes a tool called Manicod that can detect zero-day manipulated content with high accuracy.