arXiv subjects

Guobin Zhao

Publications and source records attributed to Guobin Zhao.

4 recordsLinked to original sources

arXiv2026

Chemically Meaningful Textualization Enables Explainable Validation of Metal-Organic Frameworks by Large Language Models

Computation-ready metal-organic framework (MOF) databases are essential for high-throughput screening, yet many reported crystal structures remain chemically unreasonable or disordered, compromising simulation fidelity. Existing validation approaches can identify non-computation-ready structures, but they often rely on heuristic rules, license requirement, or offer limited interpretability. Here, we show that large language models (LLMs) can serve as interpretable validators of MOF structures when crystallographic information is transformed into chemically meaningful text. By benchmarking nine descriptors, we find that successful LLM-based validation depends not on the amount of structural information alone, but on whether local coordination, framework connectivity, and chemical context are organized into a linguistically learnable representation. Fine-tuned LLMs using specialized descriptors (mof2text) achieve performance comparable to graph-based models in identifying unreasonable MOFs. Importantly, these models extend beyond black-box classification by generating diagnostic rationales for likely error sources, including abnormal bonding, connectivity, and charge states, as well as error-category predictions for annotated datasets. This work establishes chemically informed textualization as the key step that transforms LLMs from generic text models into practical and explainable tools for curating MOF databases.

cond-mat.mtrl-sci↗

arXiv2026

Physically Verifiable Evidence and LLM-Based Reporting for Bearing Fault Diagnosis

Trustworthy deployment of AI-based diagnosis in safety-critical mechanical systems hinges on validation: whether a prediction can be checked against physical reality before it is acted upon. Current intelligent fault diagnosers fail this standard in two ways. Their standard output, a class label with a softmax confidence score, is an internal statistic of the classifier, offering nothing checkable against independent physical knowledge; and the growing use of generative language models in maintenance reporting adds a second risk: hallucinated content entering reports on which decisions rest. Taking bearing fault diagnosis as the testbed, this work addresses both problems from the output side. The proposed Diagnostic Evidence Network (DENet) is an encoder-agnostic multi-task framework extending the output to a structured evidence record: the classification, a predicted characteristic frequency comparable against the theoretical value determined by bearing geometry and shaft speed, and a temporal localization of transient impulses inspectable on the raw waveform. Across four encoders and three public datasets, this evidence incurs no statistically significant accuracy cost, with a frequency error of about 6 Hz on 1,024-point segments where spectral estimation is structurally inapplicable. Centrally, the deviation between predicted and theoretical frequency constitutes a label-free, inference-time validation signal: it detects misclassifications with AUROC values of 0.970 and 0.871, and remains discriminative in the high-confidence regime where confidence-derived detectors are blind. Finally, a QLoRA-adapted language model is constrained to translate, but never generate, diagnostic content, reducing unsupported-claim rates from 10-12% to 2% and eliminating fabricated quantities.

cs.LG↗

arXiv2026

MOF-Sleuth: Tool-Grounded Reward Alignment for Explainable Fine-Grained MOF CIF Auditing

Large metal-organic framework (MOF) databases support simulation, screening, and machine learning through crystallographic information files (CIFs). Subtle chemical and structural errors in these inputs can compromise downstream results and hinder manual inspection. LLM advances in computational chemistry offer paths beyond predictive screening toward fine-grained diagnosis with evidence-grounded explanations. However, two challenges remain: (i) limited fine-grained attribution: MOF-specific validators and machine-learning models scale detection but provide fixed checks, readiness scores, or coarse labels rather than evidence-grounded explanations; and (ii) unreliable CIF reasoning: direct LLM auditing is costly and unreliable because chemical evidence is implicit across atom-site records and requires geometric, connectivity, occupancy, and charge calculations. Both stem from weak coupling between chemical evidence and language-model explanation. We introduce MOF-Sleuth, a reinforcement-guided CIF auditing agent with two modules: a deterministic Forensic Lab and a Sleuth reasoning engine. The Lab derives composition, geometry, connectivity, occupancy, coordination, and charge evidence, and Sleuth uses this evidence to produce an evidence-grounded explanation, error types, and a binary decision. Reward-guided reinforcement learning (RL) turns tool measurements into chemical explanation-level supervision, rewarding not only the final answer but also cited chemical evidence and evidence-supported diagnoses. We introduce Chemically Grounded Diagnosis (Chem-GD), a metric that assesses whether a correct diagnosis is explained by factual, relevant CIF-derived evidence. Across four benchmarks, MOF-Sleuth establishes state-of-the-art performance among LLM-based approaches and MOF-specific machine-learning methods, demonstrating gains in detection, attribution, and grounded explanation quality.

cs.AI↗

arXiv2025

MOFClassifier: A Machine Learning Approach for Validating Computation-Ready Metal-Organic Frameworks

The computational discovery and design of new crystalline materials, particularly metal-organic frameworks (MOFs), heavily relies on high-quality, computation-ready structural data. However, recent studies have revealed significant error rates within existing MOF databases, posing a critical data problem that hinders efficient high-throughput computational screening. While rule-based algorithms like MOSAEC, MOFChecker, and the Chen and Manz method (Chen-Manz) have been developed to address this, they often suffer from inherent limitations and misclassification of structures. To overcome this challenge, we developed MOFClassifier, a novel machine learning approach built upon a positive-unlabeled crystal graph convolutional neural network (PU-CGCNN) model. MOFClassifier learns intricate patterns from perfect crystal structures to predict a crystal-likeness score (CLscore), effectively classifying MOFs as computation-ready. Our model achieves a ROC value of 0.979 (previous best 0.912) and, importantly, can identify subtle structural and chemical errors that are undetectable by current rule-based methods. By accurately recovering previously misclassified false-negative structures, MOFClassifier reduces the risk of overlooking promising material candidates in large-scale computational screening campaigns. This user-friendly tool is freely available and has been integrated into the prepara-tion workflow for the updated CoRE MOF DB 2025 v1.0, contributing to accelerated computational discovery of MOF materials.

physics.chem-ph↗