Introducing MARK, the Multi-stAge Reasoning frameworK for cultural value survey response simulation, designed to enhance the accuracy, steerability, and interpretability of large language models in this task.The system is inspired by the type dynamics theory in the MBTI psychological framework for personality research.It effectively predicts and utilizes human demographic information for simulation: life-situational stress analysis, group-level personality prediction, and self-weighted cognitive imitation.Experiments on the World Values Survey show that MARK outperforms existing baselines by 10% accuracy and reduces the divergence between model predictions and human preferences.This highlights the potential of our framework to improve zero-shot personalization and help social scientists interpret model predictions.1

The Cross-lingual Dependency Parsing (XDP) task poses a significant challenge due to the differences in dependency structures between training and testing languages, known as the out-of-distribution (OOD) problem. Our research delved into this issue in the XDP dataset by selecting 43 languages from 22 language families. We found that the primary factor of the OOD problem is the unbalanced length distribution among languages. To address the impact of the OOD problem, we propose deep stable learning for Cross-lingual Dependency Parsing (SL-XDP), which utilizes deep stable learning with a feature fusion module. In detail, we implemented five feature fusion operations for generating comprehensive representations with dependency relations and the deep stable learning algorithm to decorrelate dependency structures with sequence length. Our experiments on Universal Dependencies have demonstrated that SL-XDP can lessen the impact of the OOD problem and improve the model generalization among 21 languages, with a maximum improvement of 18%.

The matching methods of question pair in the most FAQ system are less optimized for the specific domains, where proper nouns and irregular expressions always exist in the questions. To address the above problems, we propose a knowledge filtering method and the FK-BERT (FAQ-oriented knowledge-enabled BERT) model, which make full use of the domain knowledge graph. In the knowledge filtering stage, the semantic relationships between candidate entities and question sentences are thoroughly evaluated to choose the applicable entities. Furthermore, FK-BERT model considers both the relationships between entities within a single question, as well as the relationships of entities between two questions. The experimental results show that the joint use of knowledge filtering and FK-BERT model can improve the performance of FAQ systems for the domain of operating system.

Integrating with the respective advantages of XML Schema and Ontology, this paper puts forward a semantic information processing architecture-OBSA to solve the problem of heterogeneity of information sources and uncertainty of semantic. It introduces an F-Logic based semantic information presentation mechanism, presents a design of an ontology-based semantic representation language and a mapping algorithm converting Ontology to XML DTD/Schema, and an adapter architecture for accessing distributed and heterogeneous information.