Page History
...
- Diego Collarana (FIT)
- Please add yourself if you want to contribute ...
- Please add yourself if you want to contribute ...
- Please add yourself if you want to contribute ...
- ...
Short definition/description of this topic:
- Content ...
- Content ...
- Content ...
Integrating KGs into LLM Inputs (verbalize KG for LLM training)
...
- Diego Collarana (FIT)
- Daniel Baldassare (doctima)
- Michael Wetzel (Coreon)
- Sabine Mahr (word b sign)
- ...
Short definition/description of this topic:
Draft from Daniel Baldassare :
...
- Diego Collarana (FIT)
- Please add yourself if you want to contribute ...
- Please add yourself if you want to contribute ...
- Please add yourself if you want to contribute ...
- ...
Short definition/description of this topic:
- Content ...
- Content ...
- Content ...
Retrieval-Augmented Generation (RAG)
Short definition/description of this topic:
Draft Daniel Burkhardt :
- Definition of RAG
- Types of RAG
- Applications for RAG
...
- Daniel Burkhardt (FSTI)
- Robert David (SWC)
- Diego Collarana (FIT)
- Daniel Baldassare (doctima)
- Michael Wetzel (Coreon)
Short definition/description of this topic:
Draft Robert David:
- Initial RAG idea: Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
- RAG is commonly used with vector databases.
- can only grasp semantic similarity represented in the document content
- only unstructured data
- vector distance instead of a DB search limits the retrieval capabilities
- Graph RAG uses knowledge graphs as part of the RAG system
- KGs for retrieval (directly), meaning the database is storing KG data
- KGs for retrieval via a semantic layer, potentially retrieving over different data sources of structured and unstructured data
- KGs for augmenting the retrieval, meaning the queries to some database is modified via KG data
- Via Graph RAG, we can
- ingest additional semantic background knowledge (knowledge model) not represented in the data itself
- additional related knowledge based on defined paths (rule-based inference)
- focus on certain aspects of a data set for the retrieval (search configuration)
- personalization: represent different roles for retrieval via ingesting role description data into the retrieval (especially important in an enterprise environment)
- reasoning
- linked data makes factual knowledge related to the LLM-generated knowledge and thereby provide a means to check for correctness
- explainable AI: provide justifications via KG
- consolidate different data sources: unstructured, semi-structured, structured (enterprise knowledge graph scenario)
- doing the actual retrieval via KG queries: SPARQL
- hybrid retrieval: combine KG-based retrieval with vector databases or search indexes
- ingest additional semantic background knowledge (knowledge model) not represented in the data itself
...
- Daniel Burkhardt (FSTI)
- Diego Collarana (FIT)
- Daniel Baldassare (doctima)
- Please add yourself if you want to contribute ...
- ...
Short definition/description of this topic:
Draft from Daniel Burkhardt:
...
KG-Enhanced LLM Interpretability
Short definition/description of this topic:
Draft from Daniel Burkhardt:
...
- Daniel Burkhardt (FSTI)
- Please add yourself if you want to contribute ...
- Please add yourself if you want to contribute ...
- ...
Short definition/description of this topic:
- Content ...
- Content ...
- Content ...
KG-Guided Explanation Generation
...
- Daniel Burkhardt (FSTI)
- Please add yourself if you want to contribute ...
- Please add yourself if you want to contribute ...
- ...
Short definition/description of this topic:
- Content ...
- Content ...
- Content ...
KG-Based Fact-Checking and Verification
...
literatur: https://arxiv.org/abs/2404.00942, https://aclanthology.org/2023.acl-long.895.pdf, https://arxiv.org/pdf/2406.01311
Short definition/description of this topic:
- Content ...
- Content ...
- Content ...
KG-Enhanced LLM Reasoning
...
- Reasoning https://ieeexplore.ieee.org/abstract/document/10387715
- Domain focus https://arxiv.org/html/2404.10384v1
Short definition/description of this topic:
- Content ...
- Content ...
- Content ...
KG-Guided Multi-hop Reasoning
...
literature: https://neo4j.com/developer-blog/knowledge-graphs-llms-multi-hop-question-answering/, https://link.springer.com/article/10.1007/s11280-021-00911-5
Short definition/description of this topic:
- Content ...
- Content ...
- Content ...
KG-Based Consistency Checking in LLM Outputs
...
Short definition/description of this topic:
- Content ...
- Content ...
- Content ...
KGs for LLM Analysis
Using KGs to Evaluate LLM Knowledge Coverage
...
Short definition/description of this topic:
- Content ...
- Content ...
- Content ...
Analyzing LLM Biases through KG Comparisons
...
Draft from Daniel Burkhardt:
Short definition/description of this topic:
- Content ...
- Content ...
- Content ...
literature: https://arxiv.org/abs/2405.04756