Related papers: Correctness-Guaranteed Code Generation via Constra…

We propose a method to guide Large Language Models (LLMs) in generating structured content adhering to specific conventions without fine-tuning. By utilizing coroutine-based content generation constraints through a pre-agreed context-free…

Large language models (LLMs) have shown astonishing capability of generating software code, leading to its use to support developers in programming. Proposed tools have relied either on assistants for improved auto-complete or multi-agents,…

Automatically generating formal specifications including loop invariants, preconditions, and postconditions for legacy code is critical for program understanding, reuse and verification. However, the inherent complexity of control and data…

The applications of LLM Agents are becoming increasingly complex and diverse, leading to a high demand for structured outputs that can be parsed into code, structured function calls, and embodied agent commands. These developments bring…

Tasks like code generation and semantic parsing require mapping unstructured (or partially structured) inputs to well-formed, executable outputs. We introduce abstract syntax networks, a modeling framework for these problems. The outputs…

With the growing popularity of Large Language Models (LLMs) in software engineers' daily practices, it is important to ensure that the code generated by these tools is not only functionally correct but also free of vulnerabilities. Although…

A common practice in large language model (LLM) usage for complex analytical tasks such as code generation, is to sample a solution for the entire task within the model's context window. Previous works have shown that subtask decomposition…

Constrained decoding approaches aim to control the meaning or style of text generated by the pre-trained large language models (LLMs or also PLMs) for various tasks at inference time. However, these methods often guide plausible…

With the recent unprecedented advancements in Artificial Intelligence (AI) computing, progress in Large Language Models (LLMs) is accelerating rapidly, presenting challenges in establishing clear guidelines, particularly in the field of…

The capability of generating high-quality source code using large language models (LLMs) reduces software development time and costs. However, they often introduce security vulnerabilities due to training on insecure open-source data. This…

Large Language Models (LLMs) are one of the most promising developments in the field of artificial intelligence, and the software engineering community has readily noticed their potential role in the software development life-cycle.…

The hallucination of code generation models hinders their applicability to systems requiring higher safety standards. One critical bottleneck in addressing code hallucination is the difficulty of identifying the functional correctness of…

Designing diverse and safety-critical driving scenarios is essential for evaluating autonomous driving systems. In this paper, we propose a novel framework that leverages Large Language Models (LLMs) for few-shot code generation to…

Code generation models based on large language models (LLMs) have gained wide adoption, but challenges remain in ensuring safety, accuracy, and controllability, especially for complex tasks. Existing methods often lack dynamic integration…

Large pre-trained language models have recently been expanded and applied to programming language tasks with great success, often through further pre-training of a strictly-natural language model--where training sequences typically contain…

Current paradigms for code verification rely heavily on external mechanisms-such as execution-based unit tests or auxiliary LLM judges-which are often labor-intensive or limited by the judging model's own capabilities. This raises a…

Automated Driving System (ADS) is a safety-critical software system responsible for the interpretation of the vehicle's environment and making decisions accordingly. The unbounded complexity of the driving context, including unforeseeable…

Probabilistic Programming Languages (PPLs) are a powerful tool in machine learning, allowing highly expressive generative models to be expressed succinctly. They couple complex inference algorithms, implemented by the language, with an…

Pragmatic reasoning helps interlocutors infer intended meaning from ambiguous or underspecified messages by considering shared context and counterfactual alternatives. Similar challenges arise in natural language-to-code generation, where…

Code generation is to automatically generate source code conforming to a given programming specification, which has received extensive attention especially with the development of large language models (LLMs). Due to the inherent difficulty…