[KongchangAI]
Model

ArcRAG

A graph-based retrieval-augmented generation (GraphRAG) method that dynamically generates a query-local graph interface at inference time, enabling cross-construction portability of the retrieval pipeline across graph construction methods.

Timeline (last 90 days)

Nov 5

ArcRAG is a retrieval method that dynamically generates a query-local graph interface at inference time, enabling the retriever to work without co-design with a specific graph construction method.

Unverified50%
Nov 5

ArcRAG identifies entities in the question, collects reachable node labels, relation descriptors and attribute keys, and forms a local interface specific to the current query only.

Unverified50%
Nov 5

ArcRAG compiles the planned multi-hop traversal path into Cypher query statements for execution and has repair capability after execution failures.

Unverified50%
Nov 5

On the three corpora MuSiQue, HotpotQA and TriviaQA, ArcRAG cross-validated by constructing a schema-guided graph and an open information extraction graph, respectively.

Unverified50%
Nov 5

Experiments show that a construction-agnostic retriever remains effective after the graph construction method is changed, i.e., retrieval does not need to be co-designed with graph construction.

Unverified50%
Nov 5

The graph construction method (schema-guided vs. open information extraction) still affects the absolute accuracy of the final answers.

Unverified50%
Nov 5

Ablation experiments under different retry and pass budgets reveal that ArcRAG's planning, execution and repair stages each contribute to the final performance.

Unverified50%
Nov 5

ArcRAG's findings support decoupling the retrieval module from the graph construction module in GraphRAG systems, thereby reducing system integration complexity.

Unverified50%
Nov 5

ArcRAG is currently presented as a paper; specific implementation details and code availability should be referred to in the original text.

Unverified50%

All Facts (9)

Unverified

ArcRAG is a retrieval method that dynamically generates a query-local graph interface at inference time, enabling the retriever to work without co-design with a specific graph construction method.

50%
Unverified

ArcRAG identifies entities in the question, collects reachable node labels, relation descriptors and attribute keys, and forms a local interface specific to the current query only.

50%
Unverified

ArcRAG compiles the planned multi-hop traversal path into Cypher query statements for execution and has repair capability after execution failures.

50%
Unverified

On the three corpora MuSiQue, HotpotQA and TriviaQA, ArcRAG cross-validated by constructing a schema-guided graph and an open information extraction graph, respectively.

50%
Unverified

Experiments show that a construction-agnostic retriever remains effective after the graph construction method is changed, i.e., retrieval does not need to be co-designed with graph construction.

50%
Unverified

The graph construction method (schema-guided vs. open information extraction) still affects the absolute accuracy of the final answers.

50%
Unverified

Ablation experiments under different retry and pass budgets reveal that ArcRAG's planning, execution and repair stages each contribute to the final performance.

50%
Unverified

ArcRAG's findings support decoupling the retrieval module from the graph construction module in GraphRAG systems, thereby reducing system integration complexity.

50%
Unverified

ArcRAG is currently presented as a paper; specific implementation details and code availability should be referred to in the original text.

50%

Source Articles