Related papers: Multi-Grained Specifications for Distributed Syste…
Nowadays, deployment of distributed systems sets high requirements for procedures and tools for the complex testing of these systems - virtualization and cloud technologies make another level of system complexity. As a possible solution, it…
We present a bounded model checking algorithm for signal temporal logic (STL) that exploits mixed-integer linear programming (MILP). A key technical element is our novel MILP encoding of the STL semantics; it follows the idea of stable…
As the text generation capabilities of large language models become increasingly prominent, recent studies have focused on controlling particular aspects of the generated text to make it more personalized. However, most research on…
Machine learning models deployed in the open world may encounter observations that they were not trained to recognize, and they risk misclassifying such observations with high confidence. Therefore, it is essential that these models are…
We present a coverage-guided testing algorithm for distributed systems implementations. Our main innovation is the use of an abstract formal model of the system that is used to define coverage. Such abstract models are frequently developed…
Complex software systems often suffer from silent failures, i.e., violations of the intended semantics that do not cause explicit errors. A promising approach to detect such errors is to use system-specific runtime checkers that monitor the…
This paper presents the results of finetuning large language models (LLMs) for the task of detecting vulnerabilities in source code. We leverage WizardCoder, a recent improvement of the state-of-the-art LLM StarCoder, and adapt it for…
Despite Retrieval-Augmented Generation (RAG) showing promising capability in leveraging external knowledge, a comprehensive evaluation of RAG systems is still challenging due to the modular nature of RAG, evaluation of long-form responses…
Large language models (LLMs) have shown remarkable ability to generate code, yet their outputs often violate syntactic or semantic constraints when guided only through natural language prompts. We introduce TreeCoder, the most general and…
The trend towards large language models (LLMs) for guardrailing against undesired behaviors is increasing and has shown promise for censoring user inputs. However, increased latency, memory consumption, hosting expenses and non-structured…
Modern distributed systems use names everywhere. Lockservices such as Chubby and ZooKeeper provide an effective mechanism for mapping from application names to server instances, but proper usage of them requires a large amount of…
Bug triaging, the task of assigning new issues to developers, is often slow and inconsistent in large projects. We present a lightweight framework that instruction-tuned large language model (LLM) with LoRA adapters and uses…
The use of large language models for code generation is a rapidly growing trend in software development. However, without effective methods for ensuring the correctness of generated code, this trend could lead to undesirable outcomes. In…
We consider the problem of tracking the state of a process that evolves over time in a distributed setting, with multiple observers each observing parts of the state, which is a fundamental information processing problem with a wide range…
Deep learning models have proven to be highly successful. Yet, their over-parameterization gives rise to model multiplicity, a phenomenon in which multiple models achieve similar performance but exhibit distinct underlying behaviours. This…
While reachability analysis is one of the most promising approaches for formal verification of dynamic systems, a major disadvantage preventing a more widespread application is the requirement to manually tune algorithm parameters such as…
The ability to follow instructions is crucial for Large Language Models (LLMs) to handle various real-world applications. Existing benchmarks primarily focus on evaluating pure response quality, rather than assessing whether the response…
Code Large Language Models (Code LLMs) are being increasingly employed in real-life applications, so evaluating them is critical. While the conventional accuracy evaluates the performance of Code LLMs on a set of individual tasks, their…
Recent breakthroughs in Large Language Models (LLMs) have led to their adoption across a wide range of tasks, ranging from code generation to machine translation and sentiment analysis, etc. Red teaming/Safety alignment efforts show that…
Large language models (LLMs) often produce unsupported or unverifiable content, known as "hallucinations." To mitigate this, retrieval-augmented LLMs incorporate citations, grounding the content in verifiable sources. Despite such…