Verifiable Knowledge Expansion through Retrieval-Grounded Formal Concept Analysis

This paper presents a knowledge-expansion framework that combines a retrieval-augmented small language model (SLM) with formal concept analysis (FCA). Starting from seed attributes, FCA proposes implications over an expanding formal context, while the SLM validates each implication using retrieved evidence or supplies a counterexample. The system also supports incidence judgments, consistency checks, and attribute proposals, making accepted implications and corrections inspectable. In a rare-ataxia setting built from Orphadata resources, 10-seed runs achieved relation F1 scores of 0.29–0.52 and closure-based implication F1 scores of 0.22–0.30. Ablations suggest incidence judgments can help, while identifying positive object-attribute pairs remains difficult.