Search papers, labs, and topics across Lattice.
3
0
5
Frontier Chinese models excel in understanding novel xiehouyu riddles, but their creative output still lags behind human performance.
Training language models with just 100 million tokens could redefine efficiency benchmarks in Chinese NLP.
Re-ranking can make or break user engagement, and GR2 boosts performance by over 18% by harnessing the power of LLMs in ways previously unexplored.
