Large Language Models (LLMs) are powerful tools for summarizing data on well-studied topics. However, they are not good at reasoning about new topics that constantly emerge in our societies, which may not be well-represented in their training data and may also be hard to collect real-time data for. While the reasoning capabilities of LLMs are steadily improving, they still lack the depth and nuance of human reasoning.
Additionally, LLMs fall short if the data available for a topic on the internet is biased, for example, when certain viewpoints are under-represented online.
At present, LLMs also suffer from the hallucination problem, meaning they occasionally produce generate inaccurate or misleading results.
Despite these limitations, LLMs might be able to generate a valuable set of initial arguments. Humans can use this initial output as a starting point to develop more nuanced arguments or study the data retrieved to craft better questions.
AI tools can also assist with several operational tasks, such as:
- Detecting potential duplicate arguments
- Offering a second opinion on the relative strength of argument pairs
- Summarizing the information presented on a topic page