Automated Anomaly Detection for Textual Commercial Contracts: BERT-Extracted Features and Fuzzy Neighborhood Rough Sets
Authors:
- Yanfang MaYMYanfang Ma
- Zhongzhang LvZLZhongzhang Lv
- Xiran LiXLXiran Li
Preprint
- 18 August 2026
- preprint
- Published by Elsevier in SSRN Electronic Journal
Abstract
Contract anomaly detection, as one of the fundamental building blocks for contract analysis, can identify potential violations and abnormal clauses efficiently, further help to reduce legal and operational risks and evaluate whether the contract complies with regulatory requirements and internal norms. Traditional contract detection relies on legal professionals and is plagued by problems such as low efficiency, high costs, and unstable detection quality. Consequently, automated contract detection has gained significant research attention. However, existing detection methods encounter three pivotal challenges. First, the named entity recognition model based on annotation suffers from inaccurate entity boundary detection. This leads to entity extraction errors and a decrease in the model's recognition performance. Second, contract data scarcity and expensive manual annotation hinder model training. Third, effectively eliciting knowledge from large language models for contract risk detection remains a challenge. To address these challenges, this paper proposes a multi-source feature fusion approach for contract anomaly detection. Four types of features are extracted from contract texts: semantic features, structural features, keyword features and TF-IDF features. These features are then concatenated and input into the Fuzzy Neighborhood Rough Set model to perform anomaly detection. We conducted experiments on 10 datasets, and 9 unsupervised algorithms are evaluated, including both established and contemporary anomaly detection techniques. The results demonstrate that BERT-FNRS achieves favorable performance. It performs prominently in Accuracy and ROCAUC, with average values of 0.9652 and 0.9252, respectively.Keywords
This publication has 41 references indexed in Scilit:
- A survey of classification tasks and approaches for legal contractsArtificial Intelligence Review, 2025
- What matters in patent claims: structural and semantic-based feature extraction and embedding optimizationScientometrics, 2025
- Classifying ultra‐short scientific texts using a hybrid hierarchical multi‐label classification frameworkJournal of the Association for Information Science and Technology, 2025
- Efficient Hybridization of Quantum Annealing and Ant Colony Optimization for Coloring DIMACS Graph InstancesJournal of Heuristics, 2025
- Citation structural diversity: a novel metric combining structure and semantics for literature evaluationScientometrics, 2025
- Enhancing keyphrase extraction from academic articles using section structure informationScientometrics, 2025
- Anomaly detection based on weighted fuzzy-rough densityApplied Soft Computing, 2023
- Automated detection of contractual risk clauses from construction specifications using bidirectional encoder representations from transformers (BERT)Automation in Construction, 2022
- Multilingual evaluation of pre-processing for BERT-based sentiment analysis of tweetsExpert Systems with Applications, 2021
- Fuzzy rough sets: Survey and proposal of an enhanced knowledge representation model based on automatic noisy sample detectionCognitive Systems Research, 2020