Large language models as tax attorneys: a case study in legal capabilities emergence.

Better understanding of Large Language Models' (LLMs) legal analysis abilities can contribute to improving the efficiency of legal services, governing artificial intelligence and leveraging LLMs to identify inconsistencies in law. This paper explores LLM capabilities in applying tax law. We choose this area of law because it has a structure that allows us to set up automated validation pipelines across thousands of examples, requires logical reasoning and maths skills, and enables us to test LLM capabilities in a manner relevant to real-world economic lives of citizens and companies. Our experiments demonstrate emerging legal understanding capabilities, with improved performance in each subsequent OpenAI model release. We experiment with retrieving and using the relevant legal authority to assess the impact of providing additional legal context to LLMs. Few-shot prompting, presenting examples of question-answer pairs, is also found to significantly enhance the performance of the most advanced model, GPT-4. The findings indicate that LLMs, particularly when combined with prompting enhancements and the correct legal texts, can perform at high levels of accuracy but not yet at expert tax lawyer levels. As LLMs continue to advance, their ability to reason about law autonomously could have significant implications for the legal profession and AI governance. This article is part of the theme issue 'A complexity science approach to law and governance'.

Correlation of Carbonic Anhydrase VI Enzyme, Total Proteins, Antioxidant Levels of Saliva and Dental Caries in Caries-Free and Caries-Active Children - A Case-Control Study.

Background and Objectives: Factors in the biofilm influence the induction and advancement of the carious process. This study was done to relate and assess the levels of enzyme carbonic anhydrase VI, total protein, and antioxidants (superoxide dismutase [SOD], catalase, lipid peroxidase, and uric acid) in caries-free and caries-active children. Methods: This case-control study comprised 60 children of age group 6-12 years who were evaluated for decayed missing filled teeth (dmft)/DMFT criteria and distributed into two groups: Group 1 - caries active (case) and Group 2 - caries free (control) for saliva collection with 30 participants in each of the above groups. Stimulated saliva was obtained, and the samples were then evaluated using biochemical lab tests. The data were then statistically evaluated using independent t-test. Results: Catalase in the caries-free group was significantly higher, but the concentration of carbonic anhydrase (CAVI) enzyme, total protein, and other antioxidant enzyme activity was enhanced in caries-active children in which uric acid demonstrated a statistically significant difference with higher levels in caries-active group. Conclusion: There is an increased concentration of CAVI enzyme in caries-active group and total protein showed a linear relation with caries activity. Antioxidant parameters such as SOD and lipid peroxidase were increased with caries activity. Uric acid was significantly higher in the caries-active group, whereas catalase showed an indirect relation with dental caries. Significant variations in the levels of these parameters imply that the levels of these components of saliva can act as strong markers of caries status in children.