arXiv subjects

Dalal Alrajeh

Publications and source records attributed to Dalal Alrajeh.

At least 19 recordsLinked to original sources

arXiv2026

Learning to adapt GR(1) specifications through degradation

Reactive synthesis is a powerful tool for generating correct-by-construction controllers from formal specifications. GR(1) is an assume-guarantee specification framework that enables efficient synthesis, allowing synthesised controllers to be used in a wide array of applications. The limitation of such controllers is that, should they encounter environment behaviour unspecified in the assumptions of the specification, the specified system guarantees are no longer ensured. Our work proposes an approach based on oracle-guided inductive synthesis to adapt the specification to be consistent with the observed assumption violation, while degrading system guarantees as little as possible to maintain realisability. Our methodology discovers multiple potential solutions, so we propose a preference criteria, based on the ability of the specification to enable robustness under adaptation. Although our approach is capable of degrading the entire specification, for our case studies we successfully discover degradations that preserve the entire set of original guarantees.

cs.SE↗

arXiv2026

Adaptive GR(1) Specification Repair for Liveness-Preserving Shielding in Reinforcement Learning

Shielding is widely used to enforce safety in reinforcement learning (RL), ensuring that an agent's actions remain compliant with formal specifications. Classical shielding approaches, however, are often static, in the sense that they assume fixed logical specifications and hand-crafted abstractions. While these static shields provide safety under nominal assumptions, they fail to adapt when environment assumptions are violated. In this paper, we develop an adaptive shielding framework based on based on Generalized Reactivity of rank 1 (GR(1)) specifications, a tractable and expressive fragment of Linear Temporal Logic (LTL) that captures both safety and liveness properties. Our method detects environment assumption violations at runtime and employs Inductive Logic Programming (ILP) to automatically repair GR(1) specifications online, in a systematic and interpretable way. This ensures that the shield evolves gracefully, ensuring liveness is achievable and minimally weakening goals only when necessary. We consider two case studies: Minepump and Atari Seaquest; showing that (i) static symbolic controllers are often severely suboptimal when optimizing for auxiliary rewards, and (ii) RL agents equipped with our adaptive shield maintain near-optimal reward and perfect logical compliance compared with static shields.

cs.AI↗

arXiv2026

A Model for Mediating Multi-Modal Human Intent into Safe Maneuvers for UAVs

Direct human interaction with autonomous UAV systems can be enabled through modalities such as speech, gestures, and graphical interfaces. However, interpreting such inputs as directly executable commands introduces safety risks in dynamic environments. Operator requests may conflict with terrain constraints, inter-UAV separation requirements, or flight-envelope limitations. In this paper, we present a requirements-governed maneuver-response model that mediates multi-modal human intent into safe UAV maneuvers by treating operator inputs as bounded maneuver requests rather than direct commands. Requested maneuvers are mapped to constrained motion primitives and processed through a structured request-evaluate-execute pipeline. Each request is interpreted with associated confidence, validated against terrain, separation, workspace, and flight-envelope constraints, and either constrained, rejected, or executed under continuous runtime monitoring. We further formalize the approach as a requirements-based specification model in which maneuver primitives are associated with explicit preconditions, invariants, guard conditions, and postconditions governing admissibility, execution safety, and emergency handling. These requirements support runtime verification and future reactive synthesis approaches. We present an initial lab-based validation demonstrating that voice and GUI-based inputs can be reliably interpreted and safely executed as constrained maneuver requests.

cs.RO↗

arXiv2026

How Analysts Use AI in High-Stakes Crime Linkage: An Industrial Study

Crime linkage analysis is used in many countries to identify series of offences that may have been committed by the same individual. In practice, specialist analysts manually search for behavioural and situational connections across large crime databases, an effort that is time-consuming, cognitively demanding, and can involve repeated exposure to disturbing material. To support this work, an Artificial Intelligence (AI)-enabled decision-support tool was co-developed with a UK law enforcement agency to assist analysts in identifying likely crime linkages. This paper reports an industrial evaluation of the crime-linkage tool. We conducted a mixed-methods usability study combining direct observation, eye-tracking, mouse-tracking, and surveys to examine how analysts engage with AI predictions and with the model features presented as explanations. Our findings show that analysts used the AI predictions selectively and frequently validated them against behavioural (non-AI) evidence, reflecting partial trust and an ongoing reliance on established analytical practices. We also found that analysts attended to the presented model features and valued their availability, while identifying opportunities to improve how explanations are presented and integrated into the workflow. Overall, our results highlight the need for AI-enabled decision-support tools to better integrate explanations and traditional analytical methods, and demonstrate the importance of in-situ evaluation for engineering usable and trustworthy AI in high-stakes settings.

cs.HC↗

arXiv2026

Length Generalization with Log-Depth Recurrent Units

Length generalization remains a persistent challenge for neural networks: recurrent models tend to suffer from positional biases, while transformers are constrained by fixed computational depth. Regular languages provide a frequently used testbed for evaluating length generalization, as label prediction can be checked for any sequence length. We propose MLP-LDRU, a type of Log-Depth Recurrent Unit, which captures a class of associativity-biased operators designed to approximate recurrence through parallel reduction. We evaluate MLP-LDRU on 21 regular-language tasks, consisting of standard benchmarks and new prefix languages, where it achieves 100% out-of-distribution accuracy on 18 tasks and at least 99.9% on the remaining 3 when increasing max training length, outperforming comparable recurrent and attention-based models. We further evaluate MLP-LDRU beyond regular languages on ListOps and NLP classification benchmarks, where it performs competitively.

cs.LG↗

arXiv2026

Enhancing Binary Encoded Crime Linkage Analysis Using Siamese Network

Effective crime linkage analysis is crucial for identifying serial offenders and enhancing public safety. To address limitations of traditional crime linkage methods in handling high-dimensional, sparse, and heterogeneous data, we propose a Siamese Autoencoder framework that learns meaningful latent representations and uncovers correlations in complex crime data. Using data from the Violent Crime Linkage Analysis System (ViCLAS), maintained by the Serious Crime Analysis Section of the UK's National Crime Agency, our approach mitigates signal dilution in sparse feature spaces by integrating geographic-temporal features at the decoder stage. This design amplifies behavioral representations rather than allowing them to be overshadowed at the input level, yielding consistent improvements across multiple evaluation metrics. We further analyze how different domain-informed data reduction strategies influence model performance, providing practical guidance for preprocessing in crime linkage contexts. Our results show that advanced machine learning approaches can substantially enhance linkage accuracy, improving AUC by up to 9% over traditional methods while offering interpretable insights to support investigative decision-making.

cs.LG↗

arXiv2026

Data-Dependent Goal Modeling for ML-Enabled Law Enforcement Systems

Investigating serious crimes is inherently complex and resource-constrained. Law enforcement agencies (LEAs) grapple with overwhelming volumes of offender and incident data, making effective suspect identification difficult. Although machine learning (ML)-enabled systems have been explored to support LEAs, several have failed in practice. This highlights the need to align system behavior with stakeholder goals early in development, motivating the use of Goal-Oriented Requirements Engineering (GORE). This paper reports our experience applying the GORE framework KAOS to designing an ML-enabled system for identifying suspects in online child sexual abuse. We describe how KAOS supported early requirements elaboration, including goal refinement, object modeling, agent assignment, and operationalization. A key finding is the central role of data elicitation: data requirements constrain refinement choices and candidate agents while influencing how goals are linked, operationalized, and satisfied. Conversely, goal elaboration and agent assignment shape data quality expectations and collection needs. Our experience highlights the iterative, bidirectional dependencies between goals, data, and ML performance. We contribute a reference model for integrating GORE with data-driven system development, and identify gaps in KAOS, particularly the need for explicit support for data elicitation and quality management. These insights inform future extensions of KAOS and, more broadly, the application of formal GORE methods to ML-enabled systems for high-stakes societal contexts.

cs.CY↗

arXiv2025

RNN Generalization to Omega-Regular Languages

Büchi automata (BAs) recognize $ω$-regular languages defined by formal specifications like linear temporal logic (LTL) and are commonly used in the verification of reactive systems. However, BAs face scalability challenges when handling and manipulating complex system behaviors. As neural networks are increasingly used to address these scalability challenges in areas like model checking, investigating their ability to generalize beyond training data becomes necessary. This work presents the first study investigating whether recurrent neural networks (RNNs) can generalize to $ω$-regular languages derived from LTL formulas. We train RNNs on ultimately periodic $ω$-word sequences to replicate target BA behavior and evaluate how well they generalize to out-of-distribution sequences. Through experiments on LTL formulas corresponding to deterministic automata of varying structural complexity, from 3 to over 100 states, we show that RNNs achieve high accuracy on their target $ω$-regular languages when evaluated on sequences up to $8 \times$ longer than training examples, with $92.6\%$ of tasks achieving perfect or near-perfect generalization. These results establish the feasibility of neural approaches for learning complex $ω$-regular languages, suggesting their potential as components in neurosymbolic verification methods.

cs.LG↗

arXiv2025

Towards User-Centred Design of AI-Assisted Decision-Making in Law Enforcement

Artificial Intelligence (AI) has become an important part of our everyday lives, yet user requirements for designing AI-assisted systems in law enforcement remain unclear. To address this gap, we conducted qualitative research on decision-making within a law enforcement agency. Our study aimed to identify limitations of existing practices, explore user requirements and understand the responsibilities that humans expect to undertake in these systems. Participants in our study highlighted the need for a system capable of processing and analysing large volumes of data efficiently to help in crime detection and prevention. Additionally, the system should satisfy requirements for scalability, accuracy, justification, trustworthiness and adaptability to be adopted in this domain. Participants also emphasised the importance of having end users review the input data that might be challenging for AI to interpret, and validate the generated output to ensure the system's accuracy. To keep up with the evolving nature of the law enforcement domain, end users need to help the system adapt to the changes in criminal behaviour and government guidance, and technical experts need to regularly oversee and monitor the system. Furthermore, user-friendly human interaction with the system is essential for its adoption and some of the participants confirmed they would be happy to be in the loop and provide necessary feedback that the system can learn from. Finally, we argue that it is very unlikely that the system will ever achieve full automation due to the dynamic and complex nature of the law enforcement domain.

cs.CY↗

arXiv2024

Towards Achieving Energy Efficiency and Service Availability in O-RAN via Formal Verification

As Open Radio Access Networks (O-RAN) continue to expand, AI-driven applications (xApps) are increasingly being deployed enhance network management. However, developing xApps without formal verification risks introducing logical inconsistencies, particularly in balancing energy efficiency and service availability. In this paper, we argue that prior to their development, the formal analysis of xApp models should be a critical early step in the O-RAN design process. Using the PRISM model checker, we demonstrate how our results provide realistic insights into the thresholds between energy efficiency and service availability. While our models are simplified, the findings highlight how AI-informed decisions can enable more effective cell-switching policies. We position formal verification as an essential practice for future xApp development, avoiding fallacies in real-world applications and ensuring networks operate efficiently.

cs.NI↗

arXiv2024

$ω$-regular Expression Synthesis from Transition-Based Büchi Automata

A popular method for modelling reactive systems is to use $ω$-regular languages. These languages can be represented as nondeterministic Büchi automata (NBAs) or $ω$-regular expressions. Existing methods synthesise expressions from state-based NBAs. Synthesis from transition-based NBAs is traditionally done by transforming transition-based NBAs into state-based NBAs. This transformation, however, can increase the complexity of the synthesised expressions. This paper proposes a novel method for directly synthesising $ω$-regular expressions from transition-based NBAs. We prove that the method is sound and complete. Our empirical results show that the $ω$-regular expressions synthesised from transition-based NBAs are more compact than those synthesised from state-based NBAs. This is particularly the case for NBAs computed from obligation, reactivity, safety and recurrence-type LTL formulas, reporting in the latter case an average reduction of over 50%. We also show that our method successfully synthesises $ω$-regular expressions from more LTL formulas when using a transition-based instead of a state-based NBA.

cs.FL↗

arXiv2023

RECAP-KG: Mining Knowledge Graphs from Raw GP Notes for Remote COVID-19 Assessment in Primary Care

Clinical decision-making is a fundamental stage in delivering appropriate care to patients. In recent years several decision-making systems designed to aid the clinician in this process have been developed. However, technical solutions currently in use are based on simple regression models and are only able to take into account simple pre-defined multiple-choice features, such as patient age, pre-existing conditions, smoker status, etc. One particular source of patient data, that available decision-making systems are incapable of processing is the collection of patient consultation GP notes. These contain crucial signs and symptoms - the information used by clinicians in order to make a final decision and direct the patient to the appropriate care. Extracting information from GP notes is a technically challenging problem, as they tend to include abbreviations, typos, and incomplete sentences. This paper addresses this open challenge. We present a framework that performs knowledge graph construction from raw GP medical notes written during or after patient consultations. By relying on support phrases mined from the SNOMED ontology, as well as predefined supported facts from values used in the RECAP (REmote COVID-19 Assessment in Primary Care) patient risk prediction tool, our graph generative framework is able to extract structured knowledge graphs from the highly unstructured and inconsistent format that consultation notes are written in. Our knowledge graphs include information about existing patient symptoms, their duration, and their severity. We apply our framework to consultation notes of COVID-19 patients in the UK COVID-19 Clinical Assesment Servcie (CCAS) patient dataset. We provide a quantitative evaluation of the performance of our framework, demonstrating that our approach has better accuracy than traditional NLP methods when answering questions about patients.

cs.CL↗

arXiv2020

Combining Experts' Causal Judgments

Consider a policymaker who wants to decide which intervention to perform in order to change a currently undesirable situation. The policymaker has at her disposal a team of experts, each with their own understanding of the causal dependencies between different factors contributing to the outcome. The policymaker has varying degrees of confidence in the experts' opinions. She wants to combine their opinions in order to decide on the most effective intervention. We formally define the notion of an effective intervention, and then consider how experts' causal judgments can be combined in order to determine the most effective intervention. We define a notion of two causal models being \emph{compatible}, and show how compatible causal models can be merged. We then use it as the basis for combining experts' causal judgments. We also provide a definition of decomposition for causal models to cater for cases when models are incompatible. We illustrate our approach on a number of real-life examples.

cs.AI↗

arXiv2019

Learning Neural Search Policies for Classical Planning

Heuristic forward search is currently the dominant paradigm in classical planning. Forward search algorithms typically rely on a single, relatively simple variation of best-first search and remain fixed throughout the process of solving a planning problem. Existing work combining multiple search techniques usually aims at supporting best-first search with an additional exploratory mechanism, triggered using a handcrafted criterion. A notable exception is very recent work which combines various search techniques using a trainable policy. It is, however, confined to a discrete action space comprising several fixed subroutines. In this paper, we introduce a parametrized search algorithm template which combines various search techniques within a single routine. The template's parameter space defines an infinite space of search algorithms, including, among others, BFS, local and random search. We further introduce a neural architecture for designating the values of the search parameters given the state of the search. This enables expressing neural search policies that change the values of the parameters as the search progresses. The policies can be learned automatically, with the objective of maximizing the planner's performance on a given distribution of planning problems. We consider a training setting based on a stochastic optimization algorithm known as the cross-entropy method (CEM). Experimental evaluation of our approach shows that it is capable of finding effective distribution-specific search policies, outperforming the relevant baselines.

cs.AI↗

arXiv2019

Minimal Assumptions Refinement for GR(1) Specifications

Reactive synthesis is concerned with finding a correct-by-construction controller from formal specifications, typically expressed in Linear Temporal Logic (LTL). The specifications describe assumptions about an environment and guarantees to be achieved by the controller operating in that environment. If a controller exists, given the assumptions, the specification is said to be realizable. This paper focuses on finding a minimal set of assumptions that guarantee realizability in the context of counterstrategy-guided assumption refinement procedures. Specifically, we introduce the notion of minimal assumptions refinements and provide an algorithm that provably computes these with little time overhead. We show experimentally, using common benchmarks, that embedding our algorithm in state-of-the-art approaches for assumption refinement results in consistently shorter solutions than without such embedding, and allows to explore a higher number of candidate solutions. We also propose a hybrid variant for dealing with the higher sparsity of solutions in the space of minimal refinements and show that its application speeds up the identification of a solution.

cs.LO↗

arXiv2019

Learning Classical Planning Strategies with Policy Gradient

A common paradigm in classical planning is heuristic forward search. Forward search planners often rely on simple best-first search which remains fixed throughout the search process. In this paper, we introduce a novel search framework capable of alternating between several forward search approaches while solving a particular planning problem. Selection of the approach is performed using a trainable stochastic policy, mapping the state of the search to a probability distribution over the approaches. This enables using policy gradient to learn search strategies tailored to a specific distributions of planning problems and a selected performance metric, e.g. the IPC score. We instantiate the framework by constructing a policy space consisting of five search approaches and a two-dimensional representation of the planner's state. Then, we train the system on randomly generated problems from five IPC domains using three different performance metrics. Our experimental results show that the learner is able to discover domain-specific search strategies, improving the planner's performance relative to the baselines of plain best-first search and a uniform policy.

cs.AI↗

arXiv2018

Interpolation-Based GR(1) Assumptions Refinement

This paper considers the problem of assumptions refinement in the context of unrealizable specifications for reactive systems. We propose a new counterstrategy-guided synthesis approach for GR(1) specifications based on Craig's interpolants. Our interpolation-based method identifies causes for unrealizability and computes assumptions that directly target unrealizable cores, without the need for user input. Thereby, we discuss how this property reduces the maximum number of steps needed to converge to realizability compared with other techniques. We describe properties of interpolants that yield helpful GR(1) assumptions and prove the soundness of the results. Finally, we demonstrate that our approach yields weaker assumptions than baseline techniques, and finds solutions in case studies that are unsolvable via existing techniques.

cs.LO↗

arXiv2018

A Weakness Measure for GR(1) Formulae

In spite of the theoretical and algorithmic developments for system synthesis in recent years, little effort has been dedicated to quantifying the quality of the specifications used for synthesis. When dealing with unrealizable specifications, finding the weakest environment assumptions that would ensure realizability is typically a desirable property; in such context the weakness of the assumptions is a major quality parameter. The question of whether one assumption is weaker than another is commonly interpreted using implication or, equivalently, language inclusion. However, this interpretation does not provide any further insight into the weakness of assumptions when implication does not hold. To our knowledge, the only measure that is capable of comparing two formulae in this case is entropy, but even it fails to provide a sufficiently refined notion of weakness in case of GR(1) formulae, a subset of linear temporal logic formulae which is of particular interest in controller synthesis. In this paper we propose a more refined measure of weakness based on the Hausdorff dimension, a concept that captures the notion of size of the omega-language satisfying a linear temporal logic formula. We identify the conditions under which this measure is guaranteed to distinguish between weaker and stronger GR(1) formulae. We evaluate our proposed weakness measure in the context of computing GR(1) assumptions refinements.

cs.LO↗