arXiv subjects

Angelo Bongiorno

Publications and source records attributed to Angelo Bongiorno.

4 recordsLinked to original sources

arXiv2026

Evaluating LLM-Based Goal Extraction in Requirements Engineering: Prompting Strategies and Their Limitations

Due to the textual and repetitive nature of many Requirements Engineering (RE) artefacts, Large Language Models (LLMs) have proven useful to automate their generation and processing. In this paper, we discuss a possible approach for automating the Goal-Oriented Requirements Engineering (GORE) process by extracting functional goals from software documentation through three phases: actor identification, high and low-level goal extraction. To implement these functionalities, we propose a chain of LLMs fed with engineered prompts. We experimented with different variants of in-context learning and measured the similarities between input data and in-context examples to better investigate their impact. Another key element is the generation-critic mechanism, implemented as a feedback loop involving two LLMs. Although the pipeline achieved 61% accuracy in low-level goal identification, the final stage, these results indicate the approach is best suited as a tool to accelerate manual extraction rather than as a full replacement. The feedback-loop mechanism with Zero-shot outperformed stand-alone Few-shot, with an ablation study suggesting that performance slightly degrades without the feedback cycle. However, we reported that the combination of the feedback mechanism with Few-shot does not deliver any advantage, possibly suggesting that the primary performance ceiling is the prompting strategy applied to the 'critic' LLM. Together with the refinement of both the quantity and quality of the Shot examples, future research will integrate Retrieval-Augmented Generation (RAG) and Chain-of-Thought (CoT) prompting to improve accuracy.

cs.SE↗

arXiv2025

First-principles calculation of higher-order elastic constants from divided differences

A method is presented to calculate from first principles the higher-order elastic constants of a solid material. The method relies on finite strain deformations, a density functional theory approach to calculate the Cauchy stress tensor, and a recursive numerical differentiation technique homologous to the divided differences polynomial interpolation algorithm. The method is applicable as is to any material, regardless its symmetry, to calculate elastic constants of, in principle, any order. Here, we introduce conceptual framework and technical details of our method, we discuss sources of errors, we assess convergence trends, and we present selected applications. In particular, our method is used to calculate elastic constants up to the 6$^{th}$ order of two crystalline materials with the cubic symmetry, silicon and gold. To demonstrate general applicability, our method is also used to calculate the elastic constants up to the 5$^{th}$ order of $α$-quartz, a crystalline material belonging to the trigonal crystal system, and the second- and third-order elastic constants of kevlar, a material with an anisotropic bonding network. Higher order elastic constants computed with our method are validated against density functional theory calculations by comparing stress responses to large deformations derived within the continuum approximation.

cond-mat.mtrl-sci↗

arXiv2023

A first-principles method to calculate fourth-order elastic constants of solid materials

A first-principles method is presented to calculate elastic constants up to the fourth order of crystals with the cubic and hexagonal symmetries. The method relies on the numerical differentiation of the second Piola-Kirchhoff stress tensor and a density functional theory approach to compute the Cauchy stress tensors for a minimal list of strained configurations of a reference state. The number of strained configurations required to calculate the independent elastic constants of the second, third, and fourth order is 24 and 37 for crystals with the cubic and hexagonal symmetries, respectively. Here, this method is applied to five crystalline materials with the cubic symmetry (diamond, silicon, aluminum, silver, and gold) and two metals with the hexagonal close packing structure (beryllium and magnesium). Our results are compared to available experimental data and previous computational studies. Calculated linear and nonlinear elastic constants are also used, within a nonlinear elasticity treatment of a material, to predict values of volume and bulk modulus at zero temperature over an interval of pressures. To further validate our method, these predictions are compared to results obtained from explicit density functional theory calculations.

cond-mat.mtrl-sci↗

arXiv2018

Ultrahard carbon film from epitaxial two-layer graphene

Atomically thin graphene exhibits fascinating mechanical properties, although its hardness and transverse stiffness are inferior to those of diamond. To date, there hasn't been any practical demonstration of the transformation of multi-layer graphene into diamond-like ultra-hard structures. Here we show that at room temperature and after nano-indentation, two-layer graphene on SiC(0001) exhibits a transverse stiffness and hardness comparable to diamond, resisting to perforation with a diamond indenter, and showing a reversible drop in electrical conductivity upon indentation. Density functional theory calculations suggest that upon compression, the two-layer graphene film transforms into a diamond-like film, producing both elastic deformations and sp2-to-sp3 chemical changes. Experiments and calculations show that this reversible phase change is not observed for a single buffer layer on SiC or graphene films thicker than 3 to 5 layers. Indeed, calculations show that whereas in two-layer graphene layer-stacking configuration controls the conformation of the diamond-like film, in a multilayer film it hinders the phase transformation.

cond-mat.mtrl-sci↗