Related papers: Solver-based Gradual Type Migration

Although autoregressive models have dominated language modeling in recent years, there has been a growing interest in exploring alternative paradigms to the conventional next-token prediction framework. Diffusion-based language models have…

The advent of large language models (LLMs) has marked a significant milestone in the realm of artificial intelligence, with their capabilities often matching or surpassing human expertise in various domains. Among these achievements, their…

**Context:** The design of static type systems that can validate dynamically-typed programs (**gradually**) is an ongoing challenge. A key difficulty is that dynamic code rarely follows datatype-driven design. Programs instead use runtime…

Formal verification via theorem proving enables the expressive specification and rigorous proof of software correctness, but it is difficult to scale due to the significant manual effort and expertise required. While Large Language Models…

In this paper we describe how to leverage higher-order unification to type check a dependently typed language with meta-variables. The literature usually presents the unification algorithm as a standalone component, however the need to…

Elixir is a dynamically-typed functional language running on the Erlang Virtual Machine, designed for building scalable and maintainable applications. Its characteristics have earned it a surging adoption by hundreds of industrial actors…

We address the design of distributed systems with synchronous dataflow programming languages. As modular design entails handling both architectural and functional modularity, our first contribution is to extend an existing synchronous…

Python's dynamic type system, while offering significant flexibility and expressiveness, poses substantial challenges for static analysis and automated tooling, particularly in unannotated or partially annotated codebases. Existing type…

In the context of a collaboration with Berger-Levrault, an IT company producing information systems, we are working on migrating Microsoft Access monolithic applications to the web front-end and microservices back-end. Like in most software…

Recent advances in large language models (LLMs) have sparked growing interest in agentic workflows, which are structured sequences of LLM invocations intended to solve complex tasks. However, existing approaches often rely on static…

Recently, dynamically typed languages, such as Python, have gained unprecedented popularity. Although these languages alleviate the need for mandatory type annotations, types still play a critical role in program understanding and…

Large language models (LLMs) still struggle across tasks outside of high-resource languages. In this work, we investigate cross-lingual transfer to lower-resource languages where task-specific post-training data is scarce. Building on prior…

Type annotations in Python enhance maintainability and error detection. However, generating these annotations manually is error prone and requires extra effort. Traditional automation approaches like static analysis, machine learning, and…

Large language models (LLMs) exhibit remarkable capabilities across diverse tasks, yet aligning them efficiently and effectively with human expectations remains a critical challenge. This thesis advances LLM alignment by introducing novel…

Personalized Large Language Models (PLLMs) aim to align model outputs with individual user preferences, a crucial capability for user-centric applications. However, the prevalent approach of fine-tuning a separate module for each user faces…

Glitch tokens, inputs that trigger unpredictable or anomalous behavior in Large Language Models (LLMs), pose significant challenges to model reliability and safety. Existing detection methods primarily rely on heuristic embedding patterns…

Typeclasses provide an elegant and effective way of managing ad-hoc polymorphism in both programming languages and interactive proof assistants. However, the increasingly sophisticated uses of typeclasses within proof assistants, especially…

For many compiled languages, source-level types are erased very early in the compilation process. As a result, further compiler passes may convert type-safe source into type-unsafe machine code. Type-unsafe idioms in the original source and…

Learned optimizers are a crucial component of meta-learning. Recent advancements in scalable learned optimizers have demonstrated their superior performance over hand-designed optimizers in various tasks. However, certain characteristics of…

The strong performance of large language models (LLMs) raises extensive discussion on their application to code generation. Recent research suggests continuous program refinements through visible tests to improve code generation accuracy in…