Pinned Loading

1. HKUST-KnowComp/DeepRefine-Skill HKUST-KnowComp/DeepRefine-Skill Public

   An agent skill to evolve the quality of LLM-Wiki (Graphify) at test time.

   Python 85 6

2. HKUST-KnowComp/DeepRefine HKUST-KnowComp/DeepRefine Public

   Training a general LLM-based reasoning model for agent-compiled knowledge refinement that evolves any KB with multi-turn interaction history via RL.

   Python 12

3. HKUST-KnowComp/AtlasKV HKUST-KnowComp/AtlasKV Public

   [ICLR'26] AtlasKV: A scalable, effective, and general way to augment LLMs with billion-scale knowledge graphs using very little GPU memory cost.

   Python 24 5

4. HKUST-KnowComp/AutoSchemaKG HKUST-KnowComp/AutoSchemaKG Public

   This repository contains the implementation of AutoSchemaKG, a novel framework for automatic knowledge graph construction that combines schema generation via conceptualization.

   Python 785 104

5. HiRAG HiRAG Public

   [EMNLP'25 findings] This is the official repo for the paper, HiRAG: Retrieval-Augmented Generation with Hierarchical Knowledge.

   Python 554 82

6. GraphJudge GraphJudge Public

   [EMNLP'25 main] This is the official repo for the paper, Can LLMs be Good Graph Judge for Knowledge Graph Construction?

   Python 28 5