Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Reasoning01:30

Reasoning

Reasoning is the action of thinking about something in a logical, sensible way. It is integral to problem-solving, decision-making, and critical thinking. Reasoning can be inductive or deductive. Reasoning involves transforming information into conclusions, which is essential for problem-solving, decision-making, and critical thinking.
Inductive reasoning involves deriving generalizations from specific observations. This type of reasoning helps form beliefs about the world. For example,...
Reason and Intuition01:37

Reason and Intuition

The human brain processes information for decision-making using one of two routes: an intuitive system and a rational system (Epstein, 1994; popularized by Kahneman, 2011 as System 1 and System 2, respectively). The intuitive system is quick, impulsive, and operates with minimal effort, relying on emotions or habits to provide cues for what to do next, while the rational system is logical, analytical, deliberate, and methodical. Research in neuropsychology suggests that the brain can only use...
Heuristics01:21

Heuristics

Heuristics are problem-solving strategies that use mental shortcuts to simplify decision-making. Unlike algorithms, which must be followed precisely to achieve a correct result, heuristics offer a general problem-solving framework. They save time and energy but can sometimes lead to less rational decisions.
People often rely on heuristics when faced with an overload of information, limited time, low importance of the decision, limited information, or when a heuristic readily comes to mind. For...
Decision Making: P-value Method01:09

Decision Making: P-value Method

The process of hypothesis testing based on the P-value method includes calculating the P- value using the sample data and interpreting it.
First, a specific claim about the population parameter is proposed. The claim is based on the research question and is stated in a simple form. Further, an opposing statement to the claim  is also stated. These statements can act as null and alternative hypotheses:  a null hypothesis would be a neutral statement while the alternative hypothesis can have a...
Deductive Reasoning01:16

Deductive Reasoning

Deductive reasoning, or deduction, is the type of logic used in hypothesis-based science. In deductive reasoning, the pattern of thinking moves in the opposite direction as compared to inductive reasoning, which means that it uses a general principle or law to predict specific results. From those general principles, a scientist can deduce and predict the specific results that would be valid as long as the general principles are valid.
For example, a researcher can deduce specific predictions...
Biot-Savart Law: Problem-Solving00:59

Biot-Savart Law: Problem-Solving

The magnitude and direction of a magnetic field created by a steady current can be calculated using the Biot-Savart law.
Consider a mobile phone battery bank as a source of steady current, which flows through the wire connected between the two. What is the magnitude of the magnetic field created by this current at a field point P?
To estimate the magnitude of the total magnetic field, we first consider a small current element of length dl, at a distance r from the field point. Now the following...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

DBpHash: a blockchain-based dual-band perceptual hashing framework for copyright protection of purely chromatic background images.

Scientific reports·2026
Same author

A semantic bit-plane based three-layer encryption framework for secure medical images.

Scientific reports·2026
Same author

Saurashtra: An Indo-Aryan language dataset.

Data in brief·2026
See all related articles

Related Experiment Video

Updated: May 26, 2026

Humor or Rationality? The Neural Mechanisms of How Agent Type and Language Style Influence Satisfaction with Ride-Hailing Service Failure Recovery
09:53

Humor or Rationality? The Neural Mechanisms of How Agent Type and Language Style Influence Satisfaction with Ride-Hailing Service Failure Recovery

Published on: March 13, 2026

Neuro-symbolic reasoning engine for tax optimisation.

Karthika Veeramani1, Allen Joseph N2, Pavithran M2

  • 1School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, India.

Frontiers in Artificial Intelligence
|May 25, 2026
PubMed
Summary

This research introduces the Neuro-Symbolic Tax Optimizing Engine (NTOL) for automating Indian tax calculations. NTOL combines large language models with symbolic reasoning for accurate, auditable, and compliant tax computations.

Keywords:
Indian Income Tax Actexplainable AIhybrid AI systemsknowledge graphslarge language modelslegal reasoningneuro-symbolic AItax optimization

Related Experiment Videos

Last Updated: May 26, 2026

Humor or Rationality? The Neural Mechanisms of How Agent Type and Language Style Influence Satisfaction with Ride-Hailing Service Failure Recovery
09:53

Humor or Rationality? The Neural Mechanisms of How Agent Type and Language Style Influence Satisfaction with Ride-Hailing Service Failure Recovery

Published on: March 13, 2026

Area of Science:

  • Artificial Intelligence
  • Computational Law
  • Taxation

Background:

  • Automating tax calculations is complex due to the probabilistic nature of AI versus the deterministic requirements of legal compliance.
  • Existing AI systems struggle to reconcile the need for accuracy and auditability in financial and legal reasoning.

Purpose of the Study:

  • To develop and evaluate a novel neuro-symbolic approach for automating tax calculations and optimization in India.
  • To enhance the accuracy, compliance, and auditability of AI-driven tax computation systems.

Main Methods:

  • Developed the Neuro-Symbolic Tax Optimizing Engine (NTOL), integrating large language models (LLMs) with a symbolic reasoning component and a knowledge graph of Indian tax statutes.
  • Employed neural semantic parsing combined with formalized symbolic rules for immutable legal compliance.
  • Evaluated NTOL on a benchmark dataset of 20 Indian Income Tax Act scenarios, comparing it against LLM-only and Retrieval-Augmented Generation (RAG) systems.

Main Results:

  • NTOL achieved 80% accuracy, outperforming an LLM-only system (75%) and a simple RAG system (60%).
  • The neuro-symbolic approach demonstrated improved compliance, robustness to statutory complexities, and support for explainable results.
  • Inaccuracies were primarily due to knowledge graph limitations, not AI hallucinations, with the symbolic layer preventing invalid computations.

Conclusions:

  • The NTOL system offers a robust solution for automating Indian tax calculations, ensuring legal compliance and auditability.
  • Neuro-symbolic AI enhances transparency and reduces litigation risk by providing auditable computation trails.
  • This approach mitigates AI hallucinations and improves the reliability of automated tax processing.