相关论文: Rely-guarantee Reasoning about Concurrent Reactive…

Advanced test-time computing strategies are essential for scaling reasoning models, but their effectiveness is capped by the models' poor self-evaluation. We propose a pairwise Explanatory Verifier, trained via reinforcement learning…

This report describes the research, design and implementation work carried out in building the CLARE system at SRI International, Cambridge, England. CLARE was designed as a natural language processing system with facilities for reasoning…

We present Assume-Guarantee-Repair (AGR) - a novel framework which verifies that a program satisfies a set of properties and also repairs the program in case the verification fails. We consider communicating programs - these are simple…

Reinforcement Learning with Verifiable Rewards (RLVR) has improved the reasoning abilities of Large Language Models (LLMs) by using rule-based binary feedback. However, current RLVR methods typically assign the same reward to every token.…

Context: Reactive programming (RP) is a declarative programming paradigm suitable for expressing the handling of events. It enables programmers to create applications that react automatically to changes over time. Whenever a time-varying…

Retrieval-augmented generation (RAG) systems enhance large language models (LLMs) with external knowledge but are vulnerable to corpus poisoning and contamination attacks, which can compromise output integrity. Existing defenses often apply…

Multiagent AI systems require consistent communication, but we lack methods to verify that agents share the same understanding of the terms used. Natural language is interpretable but vulnerable to semantic drift, while learned protocols…

Reactive software calls for instrumentation methods that uphold the reactive attributes of systems. Runtime verification imposes another demand on the instrumentation, namely that the trace event sequences it reports to monitors are sound…

End-to-end conversational recommendation systems (CRS) generate responses by leveraging both dialog history and a knowledge base (KB). A CRS mainly faces three key challenges: (1) at each turn, it must decide if recommending a KB entity is…

Data replication is essential to ensure reliability, availability and fault-tolerance of massive distributed applications over large scale systems such as the Internet. However, these systems are prone to partitioning, which by Brewer's CAP…

In the last decade, we have witnessed exponential growth in the complexity of control systems for safety-critical applications (automotive, robots, industrial automation) and their transition to heterogeneous mixed-criticality systems…

We study the problem of automated hypersafety verification of infinite-state recursive programs. We propose an infinite class of product programs, specifically designed with recursion in mind, that reduce the hypersafety verification of a…

This study introduces Conversation Routines (CR), a structured prompt engineering framework for developing task-oriented dialog systems using Large Language Models (LLMs). While LLMs demonstrate remarkable natural language understanding…

Lighthouse projects such as CompCert, seL4, IronFleet, and DeepSpec have demonstrated that full verification of entire systems is feasible by establishing a refinement relation between an abstract system specification and an executable…

Static type systems are usually not sufficient to express all requirements on function calls. Hence, contracts with pre- and postconditions can be used to express more complex constraints on operations. Contracts can be checked at run time…

Robotic systems used in safety-critical industrial situations often rely on modular software architectures, and increasingly include autonomous components. Verifying that these modular robotic systems behave as expected requires approaches…

Rare-event prediction is critical in domains such as healthcare, finance, reliability engineering, customer support, aviation safety, where positive outcomes are infrequent yet potentially catastrophic. Extreme class imbalance biases…

Runtime verification (RV) consists in dynamically verifying that the event traces generated by single runs of a system under scrutiny (SUS) are compliant with the formal specification of its expected properties. RML (Runtime Monitoring…

Despite the impressive capabilities of large language models (LLMs) across diverse applications, they still suffer from trustworthiness issues, such as hallucinations and misalignments. Retrieval-augmented language models (RAG) have been…

The language models, especially the basic text classification models, have been shown to be susceptible to textual adversarial attacks such as synonym substitution and word insertion attacks. To defend against such attacks, a growing body…