AtlasKV integrates billion-scale KGs into LLMs parametrically with sub-linear complexity and low memory by converting triples into key-value representations handled by the model's attention.
In the generation relevance experiments, we need stronger sentence encoder to let the value embeddings in KGKV2 have enough semantics
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
AtlasKV: Augmenting LLMs with Billion-Scale Knowledge Graphs in 20GB VRAM
AtlasKV integrates billion-scale KGs into LLMs parametrically with sub-linear complexity and low memory by converting triples into key-value representations handled by the model's attention.