KoRe compresses one-hop knowledge-graph subgraphs into 20 discrete tokens that, injected into Qwen3-8B, match or beat text-based knowledge injection on three QA benchmarks while using up to 10x fewer tokens.
arXiv preprint arXiv:2408.14512 (2024)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
AGE applies adaptive masking via a learnable sampler in Transformer-based SSL to align graph and text embeddings, yielding higher accuracy on four GraphQA benchmarks for non-parametric GraphRAG.
citing papers explorer
-
KoRe: Compact Knowledge Representations for Large Language Models
KoRe compresses one-hop knowledge-graph subgraphs into 20 discrete tokens that, injected into Qwen3-8B, match or beat text-based knowledge injection on three QA benchmarks while using up to 10x fewer tokens.
-
AGE: Adaptive-masking for Graph Embedding in Graph Retrieval-Augmented Generation
AGE applies adaptive masking via a learnable sampler in Transformer-based SSL to align graph and text embeddings, yielding higher accuracy on four GraphQA benchmarks for non-parametric GraphRAG.