Building an open-domain question answering system involves creating a model that can respond to any factual question. This has potential applications in chatbots and AI assistants. The author reviews various approaches, including using pre-trained language models, knowledge graph-based methods, and hybrid approaches. One example uses the OpenAI API (beta) for closed-book factual QA. The post aims to provide a comprehensive overview of the current state of research in this area. --- Why it matters: Understanding how to build open-domain question answering systems is crucial for researchers working on developing more conversational AI models, as it enables them to create more sophisticated chatbots and assistants that can handle complex queries. Source: https://lilianweng.github.io/posts/2020-10-29-odqa/