Related papers: Program Analysis via Multiple Context Free Languag…

Large language models (LLMs) have demonstrated impressive capabilities across a wide range of coding tasks, including summarization, translation, completion, and code generation. Despite these advances, detecting code vulnerabilities…

Large language models (LLMs) are expected to offer structured Markdown responses for the sake of readability in web chatbots (e.g., ChatGPT). Although there are a myriad of metrics to evaluate LLMs, they fail to evaluate the readability…

Identifying and resolving software faults remains a challenging and resource-intensive process. Traditional fault localization techniques, such as Spectrum-Based Fault Localization (SBFL), leverage statistical analysis of test coverage but…

Constrained decoding enables Language Models (LMs) to produce samples that provably satisfy hard constraints. However, existing constrained-decoding approaches often distort the underlying model distribution, a limitation that is especially…

Large language models have transformed natural language processing, yet supervised fine-tuning (SFT) remains computationally intensive. This paper formally proves that capabilities acquired through SFT can be approximated by a base…

Autonomous cyber-physical systems (CPS) rely on the correct operation of numerous components, with state-of-the-art methods relying on machine learning (ML) and artificial intelligence (AI) components in various stages of sensing and…

Testing-based fault localization has been a research focus in software engineering in the past decades. It localizes faulty program elements based on a set of passing and failing test executions. Since whether a fault could be triggered and…

In-context learning (ICL) has emerged as a powerful capability of large language models (LLMs), enabling them to perform new tasks based on a few provided examples without explicit fine-tuning. Despite their impressive adaptability, these…

This paper focuses on the analysis of open-ended questions answered in different languages. Closed-ended questions, called contextual variables, are asked to all respondents in order to understand the relationships between the free and the…

Despite significant advances in alignment techniques, we demonstrate that state-of-the-art language models remain vulnerable to carefully crafted conversational scenarios that can induce various forms of misalignment without explicit…

Large language models (LLMs) have achieved remarkable performance in various evaluation benchmarks. However, concerns are raised about potential data contamination in their considerable volume of training corpus. Moreover, the static nature…

This thesis investigates two key phenomena in large language models (LLMs): in-context learning (ICL) and model collapse. We study ICL in a linear transformer with tied weights trained on linear regression tasks, and show that minimising…

This dissertation proves lower bounds on the inherent difficulty of deciding flow analysis problems in higher-order programming languages. We give exact characterizations of the computational complexity of 0CFA, the $k$CFA hierarchy, and…

Understanding how data moves, transforms, and persists, known as data flow, is fundamental to reasoning in procedural tasks. Despite their fluency in natural and programming languages, large language models (LLMs), although increasingly…

We present a novel parsing algorithm for all context-free languages, based on computing the relation between configurations and reaching transitions in a recursive transition network. Parsing complexity w.r.t. input length matches the state…

Nowadays, many applications do not exist independently but rely on various frameworks or libraries. The frequent evolution and the complex implementation of framework APIs induce many unexpected post-release crashes. Starting from the crash…

Recent progress in large vision-language models has driven improvements in language-based semantic navigation, where an embodied agent must reach a target object described in natural language. Yet we still lack a clear, language-focused…

Context. Risk analysis assesses potential risks in specific scenarios. Risk analysis principles are context-less; the same methodology can be applied to a risk connected to health and information technology security. Risk analysis requires…

Back in the 80s, the class of mildly context-sensitive formalisms was introduced so as to capture the syntax of natural languages. While the languages generated by such formalisms are constrained by the constant-growth property, the most…

Controlling the output of Large Language Models (LLMs) through context-sensitive constraints has emerged as a promising approach to overcome the limitations of Context-Free Grammars (CFGs) in guaranteeing generation validity. However, such…