arXiv subjects

Alessandro Berti

Publications and source records attributed to Alessandro Berti.

At least 19 recordsLinked to original sources

arXiv2026

Two-Tower Quantum Matrix Chain Multiplication: Trading Qubits for Depth

Matrix chain multiplication -- computing $\mathcal{W} = M^{(0)}\cdots M^{(K-1)}$ where $M^{(k)} \in \mathbb{R}^{P_k \times P_{k+1}}$ -- arises in scientific computing, machine learning, and graph analysis. Despite the importance of this problem, for chains of distinct matrices, the classical number of operations grows linearly with the chain length $K$ and polynomially in the matrix dimensions. We present \emph{Two-Tower Matrix Multiplication}, a quantum subroutine that encodes the product $\mathcal{W}$ of the $K$ matrices into a quantum state in circuit depth $\mathcal{O}(\max_{k} \mathrm{polylog} (P_k P_{k+1}))$, which is independent of~$K$ within the QRAM-based state-preparation model, whereas the qubit count is $\mathcal{O}\bigl(\sum_{k} \log P_k \bigr)$; the total gate count remains linear in $K$, so the gain is in the circuit depth. The construction interleaves state-preparation operators across two layers; within each layer, all operators act on disjoint registers and execute in parallel. This subroutine can be specialized for the chain-vector case, which computes the product of $K-1$ matrices applied to a vector. We prove the correctness of the subroutine for all $K$ and provide two implementations using the Qiskit and QCLAB frameworks. The subroutine is applicable to any downstream quantum algorithm that operates on a matrix encoded in the statevector, including norm estimation, graph-matrix powers, linear system solving, and quantum machine learning kernels.

quant-ph↗

arXiv2026

Beyond Control-Flow: Integrating the Resource Perspective into Multi-Collaborative Process Modeling from Text

Process modeling is a sub-domain of Business Process Management (BPM) focused on the translation of process artifacts into formal models. This task traditionally requires extensive human input and domain expertise in both BPM notations and the specific business context. While Large Language Models (LLMs) can now automate much of this manual work, current text-to-model approaches focus predominantly on the control-flow perspective-ordering activities without considering the collaborative aspect of the processes. In this paper, we introduce a resource-aware generation pipeline that produces formal BPMN 2.0 collaboration diagrams from natural-language descriptions. Rather than solely prompting an LLM for raw XML, we describe a compact, executable intermediate language with mandatory resource details defining both the organization (pool) and the role (lane). Cross-organization dependencies are materialized using the standard formal notation for such interactions-message events-while an orthogonal layout routine automatically handles the spatial arrangement of elements within pools and lanes. Experiments on ten business processes with nine LLMs show strong resource discovery while preserving control-flow quality and adding only marginal runtime overhead. This approach moves generative modeling toward a more comprehensive, multi-collaborative representation of business operations.

cs.AI↗

arXiv2026

Efficient Complex-Valued State Preparation on Bucket Brigade QRAM

Efficient quantum state preparation is a critical component in quantum algorithms that process large classical data, and it is fundamental to realizing quantum advantage in domains such as machine learning, quantum linear algebra, and quantum finance. Building on the framework of~\cite{berti2025efficient}, which integrates Bucket Brigade QRAM (BBQRAM) with a segment tree to achieve amplitude encoding in polylogarithmic query time, we present two improvements within the same architecture-aware framework. First, we remove the $U_{2\mathrm{CR}}$ subroutine by classically precomputing the rotation angles determined by the segment tree and storing these angles directly in the BBQRAM cells. The tradeoff is that the classically loaded QRAM stores precomputed fixed-point angles rather than raw subtree weights. Second, we extend the construction to complex-valued matrices $A \in \mathbb{C}^{M \times N}$ by storing a leaf phase alongside each precomputed rotation angle and using a two-step magnitude-then-phase procedure; the real signed case is naturally subsumed as a one-bit phase specialization. At unchanged $\mathcal{O}(\log_2^2(MN))$ BBQRAM query complexity, the QPU procedure reduces to BBQRAM retrievals and controlled-rotation cascades, with $\mathcal{O}(MN)$ memory cells per matrix and no reversible arithmetic on the QPU.

quant-ph↗

arXiv2026

PMAx: An Agentic Framework for AI-Driven Process Mining

Process mining provides powerful insights into organizational workflows, but extracting these insights typically requires expertise in specialized query languages and data science tools. Large Language Models (LLMs) offer the potential to democratize process mining by enabling business users to interact with process data through natural language. However, using LLMs as direct analytical engines over raw event logs introduces fundamental challenges: LLMs struggle with deterministic reasoning and may hallucinate metrics, while sending large, sensitive logs to external AI services raises serious data-privacy concerns. To address these limitations, we present PMAx, an autonomous agentic framework that functions as a virtual process analyst. Rather than relying on LLMs to generate process models or compute analytical results, PMAx employs a privacy-preserving multi-agent architecture. An Engineer agent analyzes event-log metadata and autonomously generates local scripts to run established process mining algorithms, compute exact metrics, and produce artifacts such as process models, summary tables, and visualizations. An Analyst agent then interprets these insights and artifacts to compile comprehensive reports. By separating computation from interpretation and executing analysis locally, PMAx ensures mathematical accuracy and data privacy while enabling non-technical users to transform high-level business questions into reliable process insights.

cs.AI↗

arXiv2025

Efficient Quantum State Preparation with Bucket Brigade QRAM

The preparation of data in quantum states is a critical component in the design of quantum algorithms. The cost of this step can significantly limit the realization of quantum advantage in domains such as machine learning, finance, and chemistry. One of the main approaches to achieve efficient state preparation is through the use of Quantum Random Access Memory (QRAM), a theoretical device for coherent data access with several proposed hardware implementations. In this work, we present a framework that integrates the hardware model of the Bucket Brigade QRAM (BBQRAM) with the classical data structure of the Segment Tree to achieve efficient state preparation. We introduce a memory layout that embeds a segment tree within BBQRAM memory cells by preserving the segment tree's hierarchy and supporting data retrieval in logarithmic time via specialized access primitives. We demonstrate that our method encodes a matrix $A \in \mathbb{R}^{M \times N}$ in a quantum register of $\Theta(\log_2(MN))$ qubits in $\mathcal{O}(\log_2^2(MN))$ time, {requiring a constant number of working qubits (under fixed precision) and $\mathcal{O}(MN)$ memory cells within the BBQRAM architecture.} We further illustrate the method through a numerical example. This framework provides theoretical support for quantum algorithms that assume negligible data loading overhead and establishes a foundation for designing classical-to-quantum encoding algorithms that are aware of the underlying hardware QRAM architecture.

quant-ph↗

arXiv2025

Knowledge-Driven Hallucination in Large Language Models: An Empirical Study on Process Modeling

The utility of Large Language Models (LLMs) in analytical tasks is rooted in their vast pre-trained knowledge, which allows them to interpret ambiguous inputs and infer missing information. However, this same capability introduces a critical risk of what we term knowledge-driven hallucination: a phenomenon where the model's output contradicts explicit source evidence because it is overridden by the model's generalized internal knowledge. This paper investigates this phenomenon by evaluating LLMs on the task of automated process modeling, where the goal is to generate a formal business process model from a given source artifact. The domain of Business Process Management (BPM) provides an ideal context for this study, as many core business processes follow standardized patterns, making it likely that LLMs possess strong pre-trained schemas for them. We conduct a controlled experiment designed to create scenarios with deliberate conflict between provided evidence and the LLM's background knowledge. We use inputs describing both standard and deliberately atypical process structures to measure the LLM's fidelity to the provided evidence. Our work provides a methodology for assessing this critical reliability issue and raises awareness of the need for rigorous validation of AI-generated artifacts in any evidence-based domain.

cs.AI↗

arXiv2025

CPN-Py: A Python-Based Tool for Modeling and Analyzing Colored Petri Nets

Colored Petri Nets (CPNs) are an established formalism for modeling processes where tokens carry data. Although tools like CPN Tools and CPN IDE excel at CPN-based simulation, they are often separate from modern data science ecosystems. Meanwhile, Python has become the de facto language for process mining, machine learning, and data analytics. In this paper, we introduce CPN-Py, a Python library that faithfully preserves the core concepts of Colored Petri Nets -- including color sets, timed tokens, guard logic, and hierarchical structures -- while providing seamless integration with the Python environment. We discuss its design, highlight its synergy with PM4Py (including stochastic replay, process discovery, and decision mining functionalities), and illustrate how the tool supports state space analysis and hierarchical CPNs. We also outline how CPN-Py accommodates large language models, which can generate or refine CPN models through a dedicated JSON-based format.

cs.DB↗

arXiv2024

Evaluating Large Language Models on Business Process Modeling: Framework, Benchmark, and Self-Improvement Analysis

Large Language Models (LLMs) are rapidly transforming various fields, and their potential in Business Process Management (BPM) is substantial. This paper assesses the capabilities of LLMs on business process modeling using a framework for automating this task, a comprehensive benchmark, and an analysis of LLM self-improvement strategies. We present a comprehensive evaluation of 16 state-of-the-art LLMs from major AI vendors using a custom-designed benchmark of 20 diverse business processes. Our analysis highlights significant performance variations across LLMs and reveals a positive correlation between efficient error handling and the quality of generated models. It also shows consistent performance trends within similar LLM groups. Furthermore, we investigate LLM self-improvement techniques, encompassing self-evaluation, input optimization, and output optimization. Our findings indicate that output optimization, in particular, offers promising potential for enhancing quality, especially in models with initially lower performance. Our contributions provide insights for leveraging LLMs in BPM, paving the way for more advanced and automated process modeling techniques.

cs.DB↗

arXiv2024

Leveraging Large Language Models for Enhanced Process Model Comprehension

In Business Process Management (BPM), effectively comprehending process models is crucial yet poses significant challenges, particularly as organizations scale and processes become more complex. This paper introduces a novel framework utilizing the advanced capabilities of Large Language Models (LLMs) to enhance the interpretability of complex process models. We present different methods for abstracting business process models into a format accessible to LLMs, and we implement advanced prompting strategies specifically designed to optimize LLM performance within our framework. Additionally, we present a tool, AIPA, that implements our proposed framework and allows for conversational process querying. We evaluate our framework and tool by i) an automatic evaluation comparing different LLMs, model abstractions, and prompting strategies and ii) a user study designed to assess AIPA's effectiveness comprehensively. Results demonstrate our framework's ability to improve the accessibility and interpretability of process models, pioneering new pathways for integrating AI technologies into the BPM field.

cs.DB↗

arXiv2024

Re-Thinking Process Mining in the AI-Based Agents Era

Large Language Models (LLMs) have emerged as powerful conversational interfaces, and their application in process mining (PM) tasks has shown promising results. However, state-of-the-art LLMs struggle with complex scenarios that demand advanced reasoning capabilities. In the literature, two primary approaches have been proposed for implementing PM using LLMs: providing textual insights based on a textual abstraction of the process mining artifact, and generating code executable on the original artifact. This paper proposes utilizing the AI-Based Agents Workflow (AgWf) paradigm to enhance the effectiveness of PM on LLMs. This approach allows for: i) the decomposition of complex tasks into simpler workflows, and ii) the integration of deterministic tools with the domain knowledge of LLMs. We examine various implementations of AgWf and the types of AI-based tasks involved. Additionally, we discuss the CrewAI implementation framework and present examples related to process mining.

cs.AI↗

arXiv2024

PM-LLM-Benchmark: Evaluating Large Language Models on Process Mining Tasks

Large Language Models (LLMs) have the potential to semi-automate some process mining (PM) analyses. While commercial models are already adequate for many analytics tasks, the competitive level of open-source LLMs in PM tasks is unknown. In this paper, we propose PM-LLM-Benchmark, the first comprehensive benchmark for PM focusing on domain knowledge (process-mining-specific and process-specific) and on different implementation strategies. We focus also on the challenges in creating such a benchmark, related to the public availability of the data and on evaluation biases by the LLMs. Overall, we observe that most of the considered LLMs can perform some process mining tasks at a satisfactory level, but tiny models that would run on edge devices are still inadequate. We also conclude that while the proposed benchmark is useful for identifying LLMs that are adequate for process mining tasks, further research is needed to overcome the evaluation biases and perform a more thorough ranking of the competitive LLMs.

cs.CL↗

arXiv2024

Challenges of Anomaly Detection in the Object-Centric Setting: Dimensions and the Role of Domain Knowledge

Object-centric event logs, allowing events related to different objects of different object types, represent naturally the execution of business processes, such as ERP (O2C and P2P) and CRM. However, modeling such complex information requires novel process mining techniques and might result in complex sets of constraints. Object-centric anomaly detection exploits both the lifecycle and the interactions between the different objects. Therefore, anomalous patterns are proposed to the user without requiring the definition of object-centric process models. This paper proposes different methodologies for object-centric anomaly detection and discusses the role of domain knowledge for these methodologies. We discuss the advantages and limitations of Large Language Models (LLMs) in the provision of such domain knowledge. Following our experience in a real-life P2P process, we also discuss the role of algorithms (dimensionality reduction+anomaly detection), suggest some pre-processing steps, and discuss the role of feature propagation.

cs.DB↗

arXiv2024

ProMoAI: Process Modeling with Generative AI

ProMoAI is a novel tool that leverages Large Language Models (LLMs) to automatically generate process models from textual descriptions, incorporating advanced prompt engineering, error handling, and code generation techniques. Beyond automating the generation of complex process models, ProMoAI also supports process model optimization. Users can interact with the tool by providing feedback on the generated model, which is then used for refining the process model. ProMoAI utilizes the capabilities LLMs to offer a novel, AI-driven approach to process modeling, significantly reducing the barrier to entry for users without deep technical knowledge in process modeling.

cs.DB↗

arXiv2024

PM4Py.LLM: a Comprehensive Module for Implementing PM on LLMs

pm4py is a process mining library for Python implementing several process mining (PM) artifacts and algorithms. It also offers methods to integrate PM with large language models (LLMs). This paper examines how the current paradigms of PM on LLM are implemented in pm4py, identifying challenges such as privacy, hallucinations, and the context window limit.

cs.DB↗

arXiv2024

Process Modeling With Large Language Models

In the realm of Business Process Management (BPM), process modeling plays a crucial role in translating complex process dynamics into comprehensible visual representations, facilitating the understanding, analysis, improvement, and automation of organizational processes. Traditional process modeling methods often require extensive expertise and can be time-consuming. This paper explores the integration of Large Language Models (LLMs) into process modeling to enhance the accessibility of process modeling, offering a more intuitive entry point for non-experts while augmenting the efficiency of experts. We propose a framework that leverages LLMs for the automated generation and iterative refinement of process models starting from textual descriptions. Our framework involves innovative prompting strategies for effective LLM utilization, along with a secure model generation protocol and an error-handling mechanism. Moreover, we instantiate a concrete system extending our framework. This system provides robust quality guarantees on the models generated and supports exporting them in standard modeling notations, such as the Business Process Modeling Notation (BPMN) and Petri nets. Preliminary results demonstrate the framework's ability to streamline process modeling tasks, underscoring the transformative potential of generative AI in the BPM field.

cs.SE↗

arXiv2024

Evaluating Large Language Models in Process Mining: Capabilities, Benchmarks, and Evaluation Strategies

Using Large Language Models (LLMs) for Process Mining (PM) tasks is becoming increasingly essential, and initial approaches yield promising results. However, little attention has been given to developing strategies for evaluating and benchmarking the utility of incorporating LLMs into PM tasks. This paper reviews the current implementations of LLMs in PM and reflects on three different questions. 1) What is the minimal set of capabilities required for PM on LLMs? 2) Which benchmark strategies help choose optimal LLMs for PM? 3) How do we evaluate the output of LLMs on specific PM tasks? The answer to these questions is fundamental to the development of comprehensive process mining benchmarks on LLMs covering different tasks and implementation paradigms.

cs.DB↗

arXiv2024

OCEL (Object-Centric Event Log) 2.0 Specification

Object-Centric Event Logs (OCELs) form the basis for Object-Centric Process Mining (OCPM). OCEL 1.0 was first released in 2020 and triggered the development of a range of OCPM techniques. OCEL 2.0 forms the new, more expressive standard, allowing for more extensive process analyses while remaining in an easily exchangeable format. In contrast to the first OCEL standard, it can depict changes in objects, provide information on object relationships, and qualify these relationships to other objects or specific events. Compared to XES, it is more expressive, less complicated, and better readable. OCEL 2.0 offers three exchange formats: a relational database (SQLite), XML, and JSON format. This OCEL 2.0 specification document provides an introduction to the standard, its metamodel, and its exchange formats, aimed at practitioners and researchers alike.

cs.DB↗

arXiv2024

OCEL 2.0 Resources -- www.ocel-standard.org

Process mining has become a cornerstone of process analysis and improvement over the last few years. With the widespread adoption of process mining tools and libraries, the limitations of traditional process mining to deal with event data with multiple case identifiers, i.e., object-centric event data, have become apparent. As a response, the subfield of object-centric process mining has formed, including a file format standardization attempt in the form of OCEL 1.0, unifying the insights of previous developments in capturing object-centric event data. However, discussions among researchers and practitioners have shown that the proposed OCEL 1.0 standard does not go far enough. OCEL 2.0 has been proposed as an advanced refinement, including normative and explicit object-to-object relationships, qualifiers for object-to-object and event-to-object relationships, and evolving object attribute values. This demonstration presents the OCEL 2.0 website available under the URL https://www.ocel-standard.org as a one-stop shop for the detailed specification, example event logs, and broad tool support to facilitate the adoption of the format.

cs.DB↗