1 code implementation • 8 Apr 2024 • Wenyang Hui, Chengyue Jiang, Yan Wang, Kewei Tu
It uses a strong LLM to summarize guidelines from previous tree search experiences to enhance the ability of a weak LLM.
1 code implementation • 9 Nov 2023 • HaoYi Wu, Wenyang Hui, Yezeng Chen, Weiqi Wu, Kewei Tu, Yi Zhou
Since the dataset only involves a narrow range of knowledge, it is easy to separately analyse the knowledge a model possesses and the reasoning ability it has.
1 code implementation • 18 Dec 2022 • Chengyue Jiang, Wenyang Hui, Yong Jiang, Xiaobin Wang, Pengjun Xie, Kewei Tu
We also found MCCE is very effective in fine-grained (130 types) and coarse-grained (9 types) entity typing.
Ranked #2 on Entity Typing on Open Entity