Search Results for author:
Found 7 papers, 4 papers with code
Syntriever: How to Train Your Retriever with Synthetic Data from LLMs
We propose Syntriever, a training framework for retrievers using synthetic data from black-box LLMs.
Exploring Large Language Models on Cross-Cultural Values in Connection with Training Methodology
Large language models (LLMs) closely interact with humans, and thus need an intimate understanding of the cultural values of human society.
QPaug: Question and Passage Augmentation for Open-Domain Question Answering of LLMs
In addition, to compensate for the case where the retrieved passages contain distracting information or divided opinions, we augment the retrieved passages with self-generated passages by LLMs to guide the answer extraction.
Measuring Sample Importance in Data Pruning for Language Models based on Information Entropy
In this work, we consider a data pruning method based on information entropy.
Hierarchical Position Embedding of Graphs with Landmarks and Clustering for Link Prediction
HPLC leverages the positional information of nodes based on landmarks at various levels of hierarchy such as nodes' distances to landmarks, inter-landmark distances and hierarchical grouping of clusters.
CEmb-SAM: Segment Anything Model with Condition Embedding for Joint Learning from Heterogeneous Datasets
We propose to train a single segmentation model so that the model can adapt to each sub-group.
ComDensE : Combined Dense Embedding of Relation-aware and Common Features for Knowledge Graph Completion
In the common feature extraction, we apply the common encoding function to all input embeddings.
