Related papers: A Modern Compiler for the French Tax Code
As the US tax law evolves to adapt to ever-changing politico-economic realities, tax preparation software plays a significant role in helping taxpayers navigate these complexities. The dynamic nature of tax regulations poses a significant…
Traditionally, parsing has been a laborious and error-prone component of compiler development, and most parsers for full industrial programming languages are still written by hand. The author [Zim22] shows that automatic parser generation…
Checking the compliance of software against laws, regulations and contracts is increasingly important and costly as the embedding of software into societal practices is becoming more pervasive. Moreover, the digitalised services provided by…
We present preliminary results about Legistix, a tool we are developing to automatically consolidate the French and European law. Legistix is based both on regular expressions used in several compound grammars, similar to the successive…
A typical compiler flow relies on a uni-directional sequence of translation/optimization steps that lower the program abstract representation, making it hard to preserve higher-level program information across each transformation step. On…
Compilers, while essential, are notoriously complex systems that demand prohibitively expensive human expertise to develop and maintain. The recent advancements in Large Language Models (LLMs) offer a compelling new paradigm: Neural…
Mathematical programming is widely employed across various sectors - such as logistics, energy, and workforce planning - to model and solve industrial optimisation problems, but its use requires substantial domain expertise. Large language…
Current compiler optimization reports often present complex, technical information that is difficult for programmers to interpret and act upon effectively. This paper assesses the capability of large language models (LLM) to understand…
While optimal taxation theory provides clear prescriptions for tax design, translating these insights into actual tax codes remains difficult. Existing work largely offers theoretical characterizations of optimal systems, while practical…
I describe a compiler and development environment for feature-augmented two-level morphology rules integrated into a full NLP system. The compiler is optimized for a class of languages including many or most European ones, and for rapid…
As one of the key tools in many security tasks, decompilers reconstruct human-readable source code from binaries. Yet, despite recent advances, their outputs often suffer from syntactic and semantic errors and remain difficult to read.…
Most knowledge graph use cases are data-centric, focusing on representing data entities and their semantic relationships. There are no published success stories to represent large-scale complicated business logic with knowledge graph…
Code is increasingly becoming a core data modality of modern machine learning research impacting not only the way we write code with conversational agents like OpenAI's ChatGPT, Google's Bard, or Anthropic's Claude, the way we translate…
Many software development tasks, such as implementing features and fixing bugs, begin with developers posing questions about a codebase. However, answering questions about codebases that span millions of lines of code across thousands of…
In recent years, the use of automated source code generation utilizing transformer-based generative models has expanded, and these models can generate functional code according to the requirements of the developers. However, recent research…
Coding standards are essential for maintaining consistent and high-quality code across teams and projects. Linters help developers enforce these standards by detecting code violations. However, manual linter configuration is complex and…
Can AI file your taxes? Not yet. Calculating US personal income taxes is a task that requires building an understanding of vast amounts of English text and using that knowledge to carefully compute results. We propose TaxCalcBench, a…
To take full advantage of a specific hardware target, performance engineers need to gain control on compilers in order to leverage their domain knowledge about the program and hardware. Yet, modern compilers are poorly controlled, usually…
Despite the great advance of Multimodal Large Language Models (MLLMs) in both instruction dataset building and benchmarking, the independence of training and evaluation makes current MLLMs hard to further improve their capability under the…
Ensuring compliance of norms and policies when working on administrative law cases can be difficult to manage for government organisations. Automating this process could save a lot of time, effort and ensure compliance. Prior research…