BERDS Collection The BERDS Benchmark aims to measure retrieval diversity for questions that are opinionated or invite diverse perspectives. • 5 items • Updated Sep 25 • 1
A Tale of Trust and Accuracy: Base vs. Instruct LLMs in RAG Systems Paper • 2406.14972 • Published Jun 21 • 7
Korean-Adapted Model Series Collection Korean-adapted Language Model Series • 13 items • Updated May 17 • 24
Efficient and Effective Vocabulary Expansion Towards Multilingual Large Language Models Paper • 2402.14714 • Published Feb 22 • 4
Adapting Large Language Models via Reading Comprehension Paper • 2309.09530 • Published Sep 18, 2023 • 77