Resources for hybrid preferences research where we learn how to route preference instances for human vs. AI feedback
Lj V. Miranda PRO
ljvmiranda921
AI & ML interests
NLP - multilinguality, data-centric AI
Recent Activity
updated
a Space
2 days ago
UD-Filipino/filbench-leaderboard
authored
a paper
3 days ago
FilBench: Can LLMs Understand and Generate Filipino?
updated
a collection
3 days ago
FilBench for Language Model Evaluation on Filipino
Organizations
Resources for hybrid preferences research where we learn how to route preference instances for human vs. AI feedback
Model collection for https://github.com/ljvmiranda921/calamanCy. You can find more information in each model (or dataset) card.
Models for the Shared Task on Word Embedding Evaluation for Ancient and Historical Languages. Repo: https://github.com/ljvmiranda921/LiBERTus.