Generated Knowledge Prompting for Commonsense Reasoning
This addresses the challenge of enhancing commonsense reasoning for AI systems without relying on structured knowledge bases, though it is incremental as it builds on existing prompting methods.
The paper tackles the problem of improving commonsense reasoning in language models by proposing generated knowledge prompting, which involves generating knowledge from a language model and using it as additional input for question answering, achieving state-of-the-art results on benchmarks like NumerSense, CommonsenseQA 2.0, and QASC.
It remains an open question whether incorporating external knowledge benefits commonsense reasoning while maintaining the flexibility of pretrained sequence models. To investigate this question, we develop generated knowledge prompting, which consists of generating knowledge from a language model, then providing the knowledge as additional input when answering a question. Our method does not require task-specific supervision for knowledge integration, or access to a structured knowledge base, yet it improves performance of large-scale, state-of-the-art models on four commonsense reasoning tasks, achieving state-of-the-art results on numerical commonsense (NumerSense), general commonsense (CommonsenseQA 2.0), and scientific commonsense (QASC) benchmarks. Generated knowledge prompting highlights large-scale language models as flexible sources of external knowledge for improving commonsense reasoning. Our code is available at https://github.com/liujch1998/GKP