Skip to content
Live From Europe

Thesis · livefromeurope

Dynamic Knowledge Graph Integration for Enhanced News Event Summarization

BaselineRAGversusGraphRAG

Turning raw news into a living knowledge graph, so AI can explain how events connect.

Georg Johannes Talaszlivefromeurope.eu

Scroll

01 · The problem

AI only knows the past

Language models are frozen at their training date. Classic RAG adds fresh articles, but one by one, and misses how events relate.

“Machine learning models that are trained on previous news articles are only able to speak to the past.”

Dr. Margaret Mitchell
LLM training dataLLM KNOWLEDGE GAPLLM release01.10.2024Russian influenceMoldovan electionUS election03.11.202405.11.2024BEFOREAFTER

Event correlation

How are event A and event B connected?

Temporal correlation

Which event happened first?

02 · The idea

From news to a knowledge graph

GraphRAG links events by meaning and by time. Five steps, from raw articles to an answer.

Step 1/5 · Detect events

MOLDOVAN ELECTIONUS ELECTIONMOLDOVAN ELECTIONRUSSIAN INFLUENCEUS ELECTIONMoldovaChișinăuMaia SanduEU referendumRussiaDisinformationKremlinUSASwing statesDonald TrumpKamala Harris
  1. 1Detect events

    Thousands of articles are embedded and clustered. Each cluster is one event. Noise is dropped.

    • Embeddings
    • UMAP
    • HDBSCAN
    • Outlier removal
  2. 2Build the graph

    People, places and organisations become nodes, their relations become links. Russia appears in both elections: a hidden connection.

    • Relik
    • Entity linking
    • Relation extraction
  3. 3Find communities

    The Leiden algorithm finds tightly connected groups. An LLM writes a summary for each one.

    • Leiden algorithm
    • Community summaries
  4. 4Retrieve & reason

    A question pulls in the relevant communities and the paths that connect them.

    • Community retrieval
    • LLM context ranking
  5. 5Answer

    An agent writes one summary that connects events across days: how they relate, and what came first.

    • LangChain agent

Live now

Today's European news as a knowledge graph

Stories, people, places and themes, and how they connect.

Open the LFE News Graph

03 · Experiment

BaselineRAG vs GraphRAG

BaselineRAGfinds similar texts
GraphRAGfollows the connections

79%

GraphRAG wins with LLM judges

520 evaluations · GPT-4o & Mistral Large · p < 0.001

Contextual understanding82%
Comprehensiveness79%
Accuracy76%

69%

GraphRAG preferred by experts

130 evaluations · 13 experts · p < 0.05

Human preference69%

EU policy officer, journalist, legal and data professionals, praising clarity, contextual depth and relevance.

50% = no difference between the two

04 · Conclusion

Deeper answers, at a cost

Gain

More context-rich, connected summaries across days and events.

Cost

16×slower graph construction

6×slower answers

Best for

In-depth summaries and retrospective analysis, less for real time.

LIVE FROM
EUROPE.eu

Thank you.

Georg Johannes Talasz