Related papers: 3DGen: AI-Assisted Generation of Provably Correct …
The integration of large language models (LLMs) into autonomous agents has enabled complex tool use, yet in high-stakes domains, these systems must strictly adhere to regulatory standards beyond simple functional correctness. However,…
Formality transfer is commonly framed as a symmetric bidirectional task between informal and formal registers. We argue that this framing conceals a supervision design flaw in existing benchmarks such as GYAFC: binary human rewrites encode…
While large language models (LLMs) bring not only performance but also complexity, recent work has started to turn LLMs into data generators rather than task inferencers, where another affordable task model is trained for efficient…
Formal specifications, such as pre- and post-conditions provide a solid basis for performing thorough program verification. However, developers rarely provide such formal specifications, hence if AI could help in constructing them, it would…
This paper examines how to make large language models reliable for high-stakes legal work by reducing hallucinations. It distinguishes three AI paradigms: (1) standalone generative models ("creative oracle"), (2) basic retrieval-augmented…
Appropriate test case generation is critical in software testing, significantly impacting the quality of the testing. Requirements-Based Test Generation (RBTG) derives test cases from software requirements, aiming to verify whether or not…
Recent advances in diffusion models have notably enhanced text-to-image (T2I) generation quality, but they also raise the risk of generating unsafe content. Traditional safety methods like text blacklisting or harmful content classification…
Formal deductive systems are very common in computer science. They are used to represent logics, programming languages, and security systems. Moreover, writing programs that manipulate them and that reason about them is important and…
Formal languages let us define the textual representation of data with precision. Formal grammars, typically in the form of BNF-like productions, describe the language syntax, which is then annotated for syntax-directed translation and…
Automated testing plays a crucial role in ensuring software security. It heavily relies on formal specifications to validate the correctness of the system behavior. However, the main approach to defining these formal specifications is…
Novice programmers often struggle with the formal syntax of programming languages. To assist them, we design a novel programming language correction framework amenable to reinforcement learning. The framework allows an agent to mimic human…
Autoformalization aims to convert informal mathematical proofs into machine-verifiable formats, bridging the gap between natural and formal languages. However, ensuring semantic alignment between the informal and formalized statements…
Automated theorem proving (ATP) has become an appealing domain for exploring the reasoning ability of the recent successful generative language models. However, current ATP benchmarks mainly focus on symbolic inference, but rarely involve…
Learning to use feature-rich software is a persistent challenge, but generative AI tools promise to lower this barrier by replacing complex navigation with natural language prompts. We investigated how people approach prompt-based tools for…
Artificial intelligence assisted mathematical proof has become a highly focused area nowadays. One key problem in this field is to generate formal mathematical proofs from natural language proofs. Due to historical reasons, the formal proof…
The automated generation of interactive 3D cities is a critical challenge with broad applications in autonomous driving, virtual reality, and embodied intelligence. While recent advances in generative models and procedural techniques have…
Reliable verification of proofs remains a bottleneck for training and evaluating AI systems on hard mathematical reasoning. Fully formal proofs, in languages like Lean, are easy to verify because they are unambiguous and modular. Most…
Safety- and security-critical systems have to be thoroughly tested against their specifications. The state of practice is to have _natural language_ specifications, from which test cases are derived manually - a process that is slow,…
Large language models make it easy for students to delegate writing, analysis, and problem-solving to automated systems, bypassing the effortful engagement that produces lasting understanding. We introduce a practical framework that helps…
The 3rd Generation Partnership Project (3GPP) documents is key standards in global telecommunications, while posing significant challenges for engineers and researchers in the telecommunications field due to the large volume and complexity…