On the Potential and Limitations of Few-Shot In-Context Learning to
Generate Metamorphic Specifications for Tax Preparation Software
- URL: http://arxiv.org/abs/2311.11979v1
- Date: Mon, 20 Nov 2023 18:12:28 GMT
- Title: On the Potential and Limitations of Few-Shot In-Context Learning to
Generate Metamorphic Specifications for Tax Preparation Software
- Authors: Dananjay Srinivas, Rohan Das, Saeid Tizpaz-Niari, Ashutosh Trivedi,
Maria Leonor Pacheco
- Abstract summary: Nearly 50% of taxpayers filed their individual income taxes using tax software in the U.S. in FY22.
This paper formulates the task of generating metamorphic specifications as a translation task between properties extracted from tax documents.
- Score: 12.071874385139395
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Due to the ever-increasing complexity of income tax laws in the United
States, the number of US taxpayers filing their taxes using tax preparation
software (henceforth, tax software) continues to increase. According to the
U.S. Internal Revenue Service (IRS), in FY22, nearly 50% of taxpayers filed
their individual income taxes using tax software. Given the legal consequences
of incorrectly filing taxes for the taxpayer, ensuring the correctness of tax
software is of paramount importance. Metamorphic testing has emerged as a
leading solution to test and debug legal-critical tax software due to the
absence of correctness requirements and trustworthy datasets. The key idea
behind metamorphic testing is to express the properties of a system in terms of
the relationship between one input and its slightly metamorphosed twinned
input. Extracting metamorphic properties from IRS tax publications is a tedious
and time-consuming process. As a response, this paper formulates the task of
generating metamorphic specifications as a translation task between properties
extracted from tax documents - expressed in natural language - to a contrastive
first-order logic form. We perform a systematic analysis on the potential and
limitations of in-context learning with Large Language Models(LLMs) for this
task, and outline a research agenda towards automating the generation of
metamorphic specifications for tax preparation software.
Related papers
- Metamorphic Debugging for Accountable Software [8.001739956625483]
Translating legalese into formal specifications is one challenge.
Lack of a definitive 'truth' for queries (the oracle problem) is another.
We propose that these challenges can be tackled by focusing on relational specifications.
arXiv Detail & Related papers (2024-09-24T14:45:13Z) - Learning Optimal Tax Design in Nonatomic Congestion Games [63.89699366726275]
We study how to learn the optimal tax design to maximize the efficiency in nonatomic congestion games.
It is known that self-interested behavior among the players can alleviate the system's efficiency.
arXiv Detail & Related papers (2024-02-12T06:32:53Z) - Language Models as Inductive Reasoners [125.99461874008703]
We propose a new paradigm (task) for inductive reasoning, which is to induce natural language rules from natural language facts.
We create a dataset termed DEER containing 1.2k rule-fact pairs for the task, where rules and facts are written in natural language.
We provide the first and comprehensive analysis of how well pretrained language models can induce natural language rules from natural language facts.
arXiv Detail & Related papers (2022-12-21T11:12:14Z) - Algorithmic Fairness and Vertical Equity: Income Fairness with IRS Tax
Audit Models [73.24381010980606]
This study examines issues of algorithmic fairness in the context of systems that inform tax audit selection by the IRS.
We show how the use of more flexible machine learning methods for selecting audits may affect vertical equity.
Our results have implications for the design of algorithmic tools across the public sector.
arXiv Detail & Related papers (2022-06-20T16:27:06Z) - Metamorphic Testing and Debugging of Tax Preparation Software [2.185694185279913]
We focus on an open-source tax preparation software for our case study.
We develop a randomized test-case generation strategy to systematically validate the correctness of tax preparation software.
arXiv Detail & Related papers (2022-05-10T16:10:10Z) - Who Should Go First? A Self-Supervised Concept Sorting Model for
Improving Taxonomy Expansion [50.794640012673064]
As data and business scope grow in real applications, existing need to be expanded to incorporate new concepts.
Previous works on taxonomy expansion process the new concepts independently and simultaneously, ignoring the potential relationships among them and the appropriate order of inserting operations.
We propose TaxoOrder, a novel self-supervised framework that simultaneously discovers the local hypernym-hyponym structure among new concepts and decides the order of insertion.
arXiv Detail & Related papers (2021-04-08T11:00:43Z) - Tax Knowledge Graph for a Smarter and More Personalized TurboTax [0.0]
We will share our innovative and practical approach to representing complicated U.S. and Canadian income tax compliance logic via a large-scale knowledge graph.
We will cover how the Tax Knowledge Graph is constructed and automated, how it is used to calculate tax refunds, reasoned to find missing info, and navigated to explain the calculated results.
arXiv Detail & Related papers (2020-09-13T22:41:01Z) - The AI Economist: Improving Equality and Productivity with AI-Driven Tax
Policies [119.07163415116686]
We train social planners that discover tax policies that can effectively trade-off economic equality and productivity.
We present an economic simulation environment that features competitive pressures and market dynamics.
We show that AI-driven tax policies improve the trade-off between equality and productivity by 16% over baseline policies.
arXiv Detail & Related papers (2020-04-28T06:57:18Z) - TaxoExpan: Self-supervised Taxonomy Expansion with Position-Enhanced
Graph Neural Network [62.12557274257303]
Taxonomies consist of machine-interpretable semantics and provide valuable knowledge for many web applications.
We propose a novel self-supervised framework, named TaxoExpan, which automatically generates a set of query concept, anchor concept> pairs from the existing taxonomy as training data.
We develop two innovative techniques in TaxoExpan: (1) a position-enhanced graph neural network that encodes the local structure of an anchor concept in the existing taxonomy, and (2) a noise-robust training objective that enables the learned model to be insensitive to the label noise in the self-supervision data.
arXiv Detail & Related papers (2020-01-26T21:30:21Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.