no code implementations • 15 Feb 2024 • Ting Fang Tan, Kabilan Elangovan, Liyuan Jin, Yao Jie, Li Yong, Joshua Lim, Stanley Poh, Wei Yan Ng, Daniel Lim, Yuhe Ke, Nan Liu, Daniel Shu Wei Ting
200 responses to the testing dataset were generated by 5 fine-tuned LLMs for evaluation.
no code implementations • 21 Sep 2018 • Ding Jingtao, Yu Guanghui, He Xiangnan, Li Yong, Jin Depeng
First, we find that sampling negative items from the whole space is unnecessary and may even degrade the performance.