All Posts

We present PageIndex, a reasoning-based RAG system that simulates how human experts navigate and extract knowledge from long documents through tree search.

We introduce Mafin2.5, which is built based on PageIndex, with a 98.7% accuracy rate on the finance industry question-answering benchmark.

We introduce Model augmented fine-tuning (Mafin) -- a novel approach for fine-tuning a black-box embedding model by augmenting it with a trainable embedding model.

We propose a practical acquisition function for prompt/completion pairs based on the predictive entropy of the language model and a measure of certainty of the implicit preference model optimized by DPO.