In recent years, the field of AI & Law has increasingly focused on predicting legal judgments, particularly in civil cases. While traditional neural network methods are highly effective at automatically learning patterns from large datasets, they often suffer from a lack of interpretability. To address this limitation, we propose a neuro-symbolic framework for legal judgment prediction, based on large language models (LLMs). This framework combines legal knowledge (e.g., legal rules), represented through first-order logic rules, with deep neural networks (DNNs), using (...) a discrepancy loss to minimize prediction differences between the two components. By integrating the logic module during end-to-end training, knowledge is effectively transferred to the model parameters. Additionally, we develop a Chain-of-Thought prompt that uses LLMs to extract fact elements from legal cases. These elements act as logical variables within the rules, supporting the reasoning process in the logic module and improving overall interpretability. To validate the effectiveness of this framework, we conduct extensive experiments on a large dataset of private lending cases. The results demonstrate that the framework not only improves predictive performance but also enhances the interpretability of judgment predictions. (shrink)

Corruption in the construction industry is a serious problem in China. As such, fighting this corruption has become a priority target of the Chinese government, with the main effort being to discover and prosecute its perpetrators. This study profiles the demographic characteristics of major incidences of corruption in construction. It draws on the database of the 83 complete recorded cases of construction related corruption held by the Chinese National Bureau of Corruption Prevention. Categorical variables were drawn from the database, and (...) ‘association rule mining analysis’ was used to identify associations between variables as a means of profiling perpetrators. Such profiling may be used as predictors of future incidences of corruption, and consequently to inform policy makers in their fight against corruption. The results signal corruption within the Chinese construction industry to be correlated with age, with incidences rising as managers’ approach retirement age. Moreover, a majority of perpetrators operate within government agencies, are department deputies in direct contact with projects, and extort the greatest amounts per case from second tier cities. The relatively lengthy average 6.4-year period before cases come to public attention corroborates the view that current efforts at fighting corruption remain inadequate. (shrink)

Previous studies have shown that individuals in collectivist cultures may be more corrupt than those in individualist cultures when they are interacting with outgroup members. The countries that are least corrupt, according to the Transparency International Corruption Perceptions Index, tend to have horizontal individualist cultures, with Singapore being a prominent counterexample. Can findings at the cultural level of analysis be replicated at the individual level of analysis? To answer this question the authors examined the relationship between deception and cultural orientation (...) in a Singaporean sample. The results indicate that, despite the fact that Singapore is very low in corruption on the Transparency International Corruption Perceptions Index, vertical collectivism was still able to account for the variance in deception. Theoretical and practical implications are discussed. (shrink)

This study intended to explore the current status of psychological problems of preschool teachers in Southwest China 1 year after the COVID-19 pandemic and to assess the association between mental health education and psychological problems and symptoms of psychopathology. A total of 614 preschool teachers from Southwest China were enrolled to complete the questionnaires of the Chinese Symptom Checklist. Notably, 60% of the respondents reported psychological distress with GSI T-scores ≥ 63, especially the high score was reported on obsessive-compulsive disorder, (...) interpersonal sensitivity, and phobic anxiety. Although less than half of the respondents have received mental health education last year, the teachers who received the mental health education reported lower GSI T-scores. The results demonstrated the significance of constructing the education of promoting mental health of preschool teachers, and enlightening government or managers of kindergartens to relieve the psychological problems of preschool teachers through mental health education, especially for those with the pressure of overtime. It is recommended that local governments or kindergartens should organize more mental health education for kindergarten teachers to improve their mental health as well as their teaching professionalism. (shrink)