Related papers: A Modern Compiler for the French Tax Code

Performance is one of the most important qualities of software. Several techniques have thus been proposed to improve it, such as program transformations, optimisation of software parameters, or compiler flags. Many automated software…

Recent advancements on Large Language Models (LLMs) enable AI Agents to automatically generate and execute multi-step plans to solve complex tasks. However, since LLM's content generation process is hardly controllable, current LLM-based…

We study compiled AI, a paradigm in which large language models generate executable code artifacts during a compilation phase, after which workflows execute deterministically without further model invocation. This paradigm has antecedents…

The variety of data in data lakes presents significant challenges for data analytics, as data scientists must simultaneously analyze multi-modal data, including structured, semi-structured, and unstructured data. While Large Language Models…

We propose LangProp, a framework for iteratively optimizing code generated by large language models (LLMs), in both supervised and reinforcement learning settings. While LLMs can generate sensible coding solutions zero-shot, they are often…

Current trends in Machine Learning prefer explainability even when it comes at the cost of performance. Therefore, explainable AI methods are particularly important in the field of Fraud Detection. This work investigates the applicability…

Large Language Models (LLMs) have demonstrated great promise in generating code, especially when used inside an evolutionary computation framework to iteratively optimize the generated algorithms. However, in some cases they fail to…

Mixed-integer linear programming (MILP) stands as a notable NP-hard problem pivotal to numerous crucial industrial applications. The development of effective algorithms, the tuning of solvers, and the training of machine learning models for…

Compilation errors represent a significant bottleneck in software development productivity. This paper introduces WARP (Web-Augmented Real-time Program Repairer), a novel system that leverages Large Language Models (LLMs) and dynamic…

Recent work has shown logical background knowledge can be used in learning systems to compensate for a lack of labeled training data. Many methods work by creating a loss function that encodes this knowledge. However, often the logic is…

Modern instruction-tuned large language models (LLMs) have made remarkable progress in code generation. However, these LLMs fine-tuned with standard supervised fine-tuning (SFT) sometimes generate plausible-looking but functionally…

GCC and LLVM underpin much of modern software infrastructure, relying on distinct Intermediate Representations (IRs) to drive optimizations and code generation. However, the semantic and structural differences between these IRs create…

Reinforcement learning (RL) has recently emerged as a compelling approach for enhancing the reasoning capabilities of large language models (LLMs), where an LLM generator serves as a policy guided by a verifier (reward model). However,…

According to the United States Internal Revenue Service, ``the average American spends $\$270$ and 13 hours filing their taxes''. Even beyond the U.S., tax filing requires complex reasoning, combining application of overlapping rules with…

Artificial Neural Networks (ANNs) are prevalent machine learning models that are applied across various real-world classification tasks. However, training ANNs is time-consuming and the resulting models take a lot of memory to deploy. In…

Lexicon-Grammar tables are a very rich syntactic lexicon for the French language. This linguistic database is nevertheless not directly suitable for use by computer programs, as it is incomplete and lacks consistency. Tables are defined on…

Linguine is a natural-language-inspired programming language that enables users to write programs in a fluent, controlled subset of English while preserving formal semantics. The language introduces anaphoric constructs, such as pronoun…

This work presents Past as a Guide (PaG), a simple approach for Large Language Models (LLMs) to improve the coding capabilities by integrating the past history with interactive and iterative code refinements. To be specific, inspired by…

French language models, such as CamemBERT, have been widely adopted across industries for natural language processing (NLP) tasks, with models like CamemBERT seeing over 4 million downloads per month. However, these models face challenges…

Inductive logic programming (ILP) is a form of logic-based machine learning. The goal is to induce a hypothesis (a logic program) that generalises given training examples. As ILP turns 30, we review the last decade of research. We focus on…