1 code implementation • 25 May 2023 • Zhifeng Li, Yifan Fan, Bowei Zou, Yu Hong
UFO turns LLMs into knowledge sources and produces relevant facts (knowledge statements) for the given question.
1 code implementation • 15 May 2023 • Zhifeng Li, Bowei Zou, Yifan Fan, Yu Hong
Within the experimental models, the T5-based GenCQA with KEPR obtains the best performance, which is up to 60. 91% at the primary canonical metric Inc@3.
1 code implementation • 15 May 2023 • Yanling Li, Bowei Zou, Yifan Fan, Mengxing Dong, Yu Hong
The corresponding solutions contribute to the answer-oriented reasoning on a series of well-organized and thread-aware conversational contexts.