ArgRAG builds a weighted bipolar argumentation graph from retrieved documents, computes evidence strengths with quadratic energy semantics, and classifies claims by the final strength of the claim node.
Approximating Probabilistic Inference in Statistical EL with Knowledge Graph Embeddings
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Statistical information is ubiquitous but drawing valid conclusions from it is prohibitively hard. We explain how knowledge graph embeddings can be used to approximate probabilistic inference efficiently using the example of Statistical EL (SEL), a statistical extension of the lightweight Description Logic EL. We provide proofs for runtime and soundness guarantees, and empirically evaluate the runtime and approximation quality of our approach.
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ArgRAG: Explainable Retrieval Augmented Generation using Quantitative Bipolar Argumentation
ArgRAG builds a weighted bipolar argumentation graph from retrieved documents, computes evidence strengths with quadratic energy semantics, and classifies claims by the final strength of the claim node.