You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Talk 1 – Integrating Knowledge Graph with Large Language Model: From the Perspective of Knowledge Engineering (Prof Qi)
Introduction of KG and LLM
KG for LLM (1) pretraining (2) as prompt (e.g., KAPING) (3) fine-tuning (4) inference (reduce the hallucination) (5) RAG (6) knowledge update or edit (7) knowledge fusion (8) knowledge validation (as benchmark) (9) future: learning of symbolic knowledge, benchmark, improve the interpretable reasoning of llm
LLM for KG (1) entity and relation extraction (in-context learning & SFT) (2) triple generation (3) ontology matching (e.g., olala) (4) entity alignment (e.g., chatea) (5) KBQA (e.g., ELLMKGQA framework) (6) ontology reasoning (data construction: subsumption checking + instance checking) (7) KG reasoning (kg embedding is enhanced, e.g., KoPA)
KG&LLM integration (1) knowledge service platform based on KG&LLM Integration (2) OpenKG + Tool + Application
Talk 2 Industry-level KG platform
Opportunities and Challenges
Data driven enhancement of LLM and KG in enterprise digital scenarios (LLM only? KG enhanced LLM? LLM augmented KG? KG only?)
Business growth
Risk control
Knowledge construction
Opportunities and challenges of kg technology development
Lack of unified knowledge modeling methods
High cost of knowledge construction and acquisition
Opensource works: SPG (Semantic-enhanced Programmable Graph)
Schema design: everything as classes, unique instances
L1-L3 development: Pay as you go, domain constraints, evolving of different data
Subject/object type definition
KG construction based on structured data
Predicate semantics and logical symbols
Event extraction based on KG construction pipeline (subgraph query)
Implementing logic chain based on the semantic logic
Graph leaning subgraph sampling based on GNN
Applications:
Event evolving KG, interpretable reasoning
AntKnowledge Graph platform
Future
SPG and LLM bidirectionally driven controllable AI
Continuously update semantic representation
AI framework based on the OpenSPG knowledge engine
KG are better instruction synthesizer of LLMs
Github link of OpenSPG
Talk 3 KG enhanced LLM fine-tuning and applications
Our existing works
Knowledge Extraction
Existing works: Domain NER, RE; continual event extraction, doc-level causality identification
Continual RE: can learn new relations (e.g., CEAR – continual extraction for analogous relations)
Knowledge Fusion
Existing works: embedding based entity alignment, human in the loop, knowledge transfer (about blockchain, VLDB 2024), benchmark
How to use KG for fine-tuning?
KnowLA:
Talk 4 OneEdit: a neural symbolic collaboratively Knowledge Editing System
Motivation: Why knowledge editing? Fresh/conflict knowledge update and sensitive knowledge remove [picture]
System design (3 parts): interpreter (recognize and extract triples), controller (conflict resolution, kg judgement, kg augmentation), editor (an opensource tool, + a cache for rollback)
Conflict resolution: conflict identification + knowledge editing
Evaluation metrics: reliability, locality (limited edit is better), portability (reverse, one-hop, sub replace) [这很奇怪,万一发生一个牵一发而动全身的修改呢?如英女王?奥运金牌更新?- answer:this is only a prototype system with 2 small kgs]
Future work: Control Machine for Trustworthy AI
Talk 5 Leveraging LLMs few-shot learning to improve instruction drive KG construction
Motivation: traditional methods (human crafted, e.g,. TextRunner and KnowItAll) – cannot see new entities, other (automatically RE and EE) – error propagation
Main idea: utilize LLM to construct KG and incorporate user instruction (from CCKS 2023)
Talk 6 SPIREX: LLM-based relation extraction (medical KG)
RNA-KG: standard bio-medical ontologies, 600K nodes, 12.5M directed edges
PM
Industry Talk: Integrating GenAI with Graph: Innovations and Insights from NebulaGraph
Structural Data RAG
Is GraphRAG costly? No.
GraphRAG vs KG-RAG (more ideal case, the indexing involves KG construction, …)
NebulaGraph RAG – Enterprise KG system
Blog: - siwei.io
Paper Talk 1: Research Trends for the Interplay between Large Language Models and Knowledge Graphs
LLM for KGs
KG construction:
o Ontology Creation (concept extraction, property identification, ontology alignment, text-to-ontology mapping, ontology learning)
o Entity Extraction and Alignment
o Relation Extraction (supervised, few-shot, zero-shot)
KG-to-Text generation
KG reasoning
KG completion
KG embedding
KG validation (fact checking, inconsistency detection)
KG enhanced LLM
RAG
GraphRAG
LLM-KG Cooperation
KGQA
o Multi-hop question generation
o Complex or multi-hop QA
o Query generation from text
o Querying LLMs with SPARQL
o KG chatbots
The text was updated successfully, but these errors were encountered:
Talk 1 – Integrating Knowledge Graph with Large Language Model: From the Perspective of Knowledge Engineering (Prof Qi)
Introduction of KG and LLM
KG for LLM (1) pretraining (2) as prompt (e.g., KAPING) (3) fine-tuning (4) inference (reduce the hallucination) (5) RAG (6) knowledge update or edit (7) knowledge fusion (8) knowledge validation (as benchmark) (9) future: learning of symbolic knowledge, benchmark, improve the interpretable reasoning of llm
LLM for KG (1) entity and relation extraction (in-context learning & SFT) (2) triple generation (3) ontology matching (e.g., olala) (4) entity alignment (e.g., chatea) (5) KBQA (e.g., ELLMKGQA framework) (6) ontology reasoning (data construction: subsumption checking + instance checking) (7) KG reasoning (kg embedding is enhanced, e.g., KoPA)
KG&LLM integration (1) knowledge service platform based on KG&LLM Integration (2) OpenKG + Tool + Application
Talk 2 Industry-level KG platform
Opportunities and Challenges
Data driven enhancement of LLM and KG in enterprise digital scenarios (LLM only? KG enhanced LLM? LLM augmented KG? KG only?)
Opportunities and challenges of kg technology development
Opensource works: SPG (Semantic-enhanced Programmable Graph)
Schema design: everything as classes, unique instances
L1-L3 development: Pay as you go, domain constraints, evolving of different data
Subject/object type definition
KG construction based on structured data
Predicate semantics and logical symbols
Event extraction based on KG construction pipeline (subgraph query)
Implementing logic chain based on the semantic logic
Graph leaning subgraph sampling based on GNN
Applications:
Event evolving KG, interpretable reasoning
AntKnowledge Graph platform
Future
SPG and LLM bidirectionally driven controllable AI
Continuously update semantic representation
AI framework based on the OpenSPG knowledge engine
KG are better instruction synthesizer of LLMs
Github link of OpenSPG
Talk 3 KG enhanced LLM fine-tuning and applications
Our existing works
Knowledge Extraction
Existing works: Domain NER, RE; continual event extraction, doc-level causality identification
Knowledge Fusion
Existing works: embedding based entity alignment, human in the loop, knowledge transfer (about blockchain, VLDB 2024), benchmark
How to use KG for fine-tuning?
KnowLA:
Configuration translation (the problem from theory lab)
Future Directions
LLM PERF good!
Talk 4 OneEdit: a neural symbolic collaboratively Knowledge Editing System
Motivation: Why knowledge editing? Fresh/conflict knowledge update and sensitive knowledge remove [picture]
System design (3 parts): interpreter (recognize and extract triples), controller (conflict resolution, kg judgement, kg augmentation), editor (an opensource tool, + a cache for rollback)
Conflict resolution: conflict identification + knowledge editing
Evaluation metrics: reliability, locality (limited edit is better), portability (reverse, one-hop, sub replace) [这很奇怪,万一发生一个牵一发而动全身的修改呢?如英女王?奥运金牌更新?- answer:this is only a prototype system with 2 small kgs]
Future work: Control Machine for Trustworthy AI
Talk 5 Leveraging LLMs few-shot learning to improve instruction drive KG construction
Motivation: traditional methods (human crafted, e.g,. TextRunner and KnowItAll) – cannot see new entities, other (automatically RE and EE) – error propagation
Main idea: utilize LLM to construct KG and incorporate user instruction (from CCKS 2023)
Talk 6 SPIREX: LLM-based relation extraction (medical KG)
RNA-KG: standard bio-medical ontologies, 600K nodes, 12.5M directed edges
PS Streaming Graph Processing
Streaming data processing
Stream graph processing
PM
Industry Talk: Integrating GenAI with Graph: Innovations and Insights from NebulaGraph
Structural Data RAG
Is GraphRAG costly? No.
GraphRAG vs KG-RAG (more ideal case, the indexing involves KG construction, …)
NebulaGraph RAG – Enterprise KG system
Blog: - siwei.io
Paper Talk 1: Research Trends for the Interplay between Large Language Models and Knowledge Graphs
LLM for KGs
o Ontology Creation (concept extraction, property identification, ontology alignment, text-to-ontology mapping, ontology learning)
o Entity Extraction and Alignment
o Relation Extraction (supervised, few-shot, zero-shot)
KG enhanced LLM
LLM-KG Cooperation
o Multi-hop question generation
o Complex or multi-hop QA
o Query generation from text
o Querying LLMs with SPARQL
o KG chatbots
The text was updated successfully, but these errors were encountered: