2026-09-19T08:40:39Zhttps://iris.unitn.it/oai/request

oai:iris.unitn.it:11572/4574102026-04-03T00:48:09Zcom_11572_237821com_11572_101871col_11572_237822ou_ou00801

Reflexive Composition: Bidirectional Enhancement of Language Models and Knowledge Graphs Mehta, Virendra Kumar Mehta, Virendra Kumar Giunchiglia, Fausto Casati, Fabio Large Language Models, Knowledge Graphs, LLM Hallucination Reduction, Knowledge Graph Evolu-tion, Bias Mitigation Large Language Models (LLMs) have significantly advanced natural language processing, yet they con- tinue to face limitations such as hallucinations, factual inconsistencies, and restricted domain-specific knowledge. Knowledge Graphs (KGs), by contrast, provide structured and verifiable information but are expensive to build and maintain manually. This thesis introduces Reflexive Composition, a bidirectional integration framework in which LLMs and KGs iteratively refine each other’s outputs. The framework consists of three interconnected components: (1) LLM2KG, where LLMs assist in the construction and updating of domain-specific knowledge graphs; (2) Human-in-the-Loop (HITL) validation, which supports structured expert review; and (3) KG2LLM, which conditions LLM outputs on verified knowledge to reduce hallucinations and improve consistency. The methodology is evaluated across three case studies: temporal knowledge management, privacy- preserving data integration, and historical bias mitigation. Results include a 23% increase in knowledge extraction accuracy (F1 score from 0.65 to 0.80), a 28.7% reduction in LLM hallucination rates, and measurable improvements in validation efficiency through structured workflows. Reflexive Composition offers a reproducible approach for improving the reliability, scalability, and transparency of AI systems in dynamic or high-risk domains. 2025-06-20 info:eu-repo/semantics/doctoralThesis https://hdl.handle.net/11572/457410 http://dx.doi.org/10.15168/11572_457410 10.15168/11572_457410 eng firstpage:1 lastpage:178 numberofpages:178 info:eu-repo/semantics/openAccess Università degli studi di Trento place:TRENTO license:Tutti i diritti riservati (All rights reserved) license uri:iris.PRI01