Large Language Models (LLMs) provide strong summarization tools and can be used to summarize data on well-studied topics. However, they are not good at analyzing new topics that constantly emerge in our societies, which have been missing in their training data and may also be hard to collect real-time data for.
Additionally, LLMs fall short if the data available for a topic on the internet is biased, for example, when certain viewpoints are over-represented online.
LLMs also suffer from the hallucination problem, meaning they occasionally produce very incorrect results.
Despite these limitations, LLMs can sometimes generate a valuable set of initial arguments. Humans can then refine these arguments or study the retrieved data to create more focused topics.