Related papers: Mechanised Hypersafety Proofs about Structured Dat…
Hypersafety properties of arity $n$ are program properties that relate $n$ traces of a program (or, more generally, traces of $n$ programs). Classic examples include determinism, idempotence, and associativity. A number of relational…
Given that substantial amounts of domain-specific knowledge are stored in structured formats, such as web data organized through HTML, Large Language Models (LLMs) are expected to fully comprehend this structured information to broaden…
Large language models (LLMs) employ safety mechanisms to prevent harmful outputs, yet these defenses primarily rely on semantic pattern matching. We show that encoding harmful prompts as coherent mathematical problems -- using formalisms…
How can we best encode structured data into sequential form for use in large language models (LLMs)? In this work, we introduce a parameter-efficient method to explicitly represent structured data for LLMs. Our method, GraphToken, learns an…
Authenticated data structures allow untrusted third parties to carry out operations which produce proofs that can be used to verify an operation's output. Such data structures are challenging to develop and implement correctly. This paper…
Automatic synthesis from linear temporal logic (LTL) specifications is widely used in robotic motion planning, control of autonomous systems, and load distribution in power networks. A common specification pattern in such applications…
Structured data, such as tables, graphs, and databases, play a critical role in plentiful NLP tasks such as question answering and dialogue system. Recently, inspired by Vision-Language Models, Graph Neutral Networks (GNNs) have been…
Leveraging outputs from multiple large language models (LLMs) is emerging as a method for harnessing their power across a wide range of tasks while mitigating their capacity for making errors, e.g., hallucinations. However, current…
Large language models (LLMs) have achieved remarkable multi-step reasoning capabilities across various domains. However, LLMs still face distinct challenges in complex logical reasoning, as (1) proof-finding requires systematic exploration…
This survey investigates how ontologies, semantic log processing, and Large Language Models (LLMs) enhance cybersecurity. Ontologies structure domain knowledge, enabling interoperability, data integration, and advanced threat analysis.…
Mathematical reasoning remains challenging for LLMs due to complex logic and the need for precise computation. Existing methods enhance LLM reasoning by synthesizing datasets through problem rephrasing, but face issues with generation…
Current text generation models are trained using real data which can potentially contain sensitive information, such as confidential patient information and the like. Under certain conditions output of the training data which they have…
Large Language Models (LLMs) are unable to reliably reason about specific physical systems. Attempts to imbue LLMs with knowledge of the necessary physics concepts have shown great promise, but explainability and validation remain open…
Temporal Knowledge Graphs (TKGs) represent dynamic facts as timestamped relations between entities. TKG completion involves forecasting missing or future links, requiring models to reason over time-evolving structure. While LLMs show…
Logical fallacy uses invalid or faulty reasoning in the construction of a statement. Despite the prevalence and harmfulness of logical fallacies, detecting and classifying logical fallacies still remains a challenging task. We observe that…
This paper introduces a new methodology for using LLM-based systems for accurate and efficient semantic tagging of UN Security Council resolutions. The main goal is to leverage LLM performance variability to build ensemble systems for data…
The application of machine learning on tabular data in specialized domains is severely limited by data scarcity. While generative models offer a solution, traditional methods falter in low-data regimes, and recent Large Language Models…
Recent Large Language Models (LLMs) have significantly advanced natural language processing and automated decision-making. However, these models still encounter difficulties when performing complex reasoning tasks involving logical…
This paper introduces LOGSAFE, a defense mechanism for federated learning in time series settings, particularly within cyber-physical systems. It addresses poisoning attacks by moving beyond traditional update-similarity methods and instead…
A new logic for verification of security policies is proposed. The logic, HyperLTL, extends linear-time temporal logic (LTL) with connectives for explicit and simultaneous quantification over multiple execution paths, thereby enabling…