Searcharxiv⌕ Search

arXiv subjects

Haojie Sun

Publications and source records attributed to Haojie Sun.

2 recordsLinked to original sources

From Fluent Text to Ontology-Compatible Definitions: A Quality-Control Agentic Workflow

Biomedical ontologies are structured knowledge systems that must evolve continuously to represent newly emerging knowledge, but their manual maintenance remains time-consuming and laborintensive. Textual definitions are especially costly because they must be readable to humans and compatible with controlled entities, relations, and logical constraints. Large language models (LLMs) offer a promising way to assist ontology engineering tasks, including definition generation. However, textual plausibility does not guarantee knowledge-system compatibility. A generated definition may be fluent and close to a reference definition, yet still fail to ground its implied entities or violate ontology-level constraints. Directly inserting such definitions into ontology libraries may therefore introduce entity-level hallucinations and logical inconsistencies. To address this problem, we propose two structured-knowledge incompatibility metrics, Entity Error Rate (EER) and Logical Inconsistency Rate (LIR), to quantify entity grounding and logical consistency for LLM-generated ontology definitions. We further develop an agentic quality-control (QC) workflow that treats definition generation as an iterative process rather than a direct decoding step: it generates definitions, extracts axioms, checks entity existence and logical consistency, and uses the resulting diagnostics to drive repair loops. Comprehensive experiments on Disease Ontology, Uberon Ontology, and Uberon-ConstraintStress demonstrate that EER and LIR complement conventional reference-based metrics by evaluating whether generated content can be grounded and checked inside the target ontology. The workflow effectively decreases EER while maintaining strong conventional text-generation performance. LIR further exposes sparse ontology-level logical failures that are invisible to text similarity metrics, although their repair remains limited.

cs.AI↗

Triple-well ferroelectricity and kagome-like Chern flat band in two-dimensional multiferroic CuVP$_2$Se$_6$

Two-dimensional multiferroics that host nontrivial topological bands offer a rich platform for correlated and tunable quantum phenomena, yet such materials remain rare. Here, using first-principles calculations, we reveal that monolayer CuVP$_2$Se$_6$ unites a tunable triple-well ferroelectric transition with a spin-polarized Chern flat band. The ferroelectric and paraelectric phases are close in energy and can be reversibly switched by moderate strain or an electric field. During the transition, a kagome-like flat band emerges near the Fermi level, which we describe via a minimal three-orbital tight-binding model on a triangular lattice. Furthermore, the system exhibits sizable magnetic anisotropy and a magnetization-dependent Chern insulating state: the Chern number is $C = \pm 1$ for out-of-plane magnetization but becomes trivial when the moments rotate in-plane. These findings establish CuVP$_2$Se$_6$ as a promising candidate for exploring electrically tunable flat-band correlations and topological magnetism in a multiferroic monolayer.

cond-mat.mtrl-sci↗