Fatemeh Mohammadi

Fatemeh Mohammadi, Jessica Sidman, Louis Theran

Applications of algebraic geometry have sparked much recent work on algebraic matroids. An algebraic matroid encodes algebraic dependencies among coordinate functions on a variety. We study the behavior of algebraic matroids under joins and secants of varieties. Motivated by Terracini's lemma, we introduce the notion of a Terracini union of matroids, which captures when the algebraic matroid of a join coincides with the matroid union of the algebraic matroids of its summands. We illustrate applications of our results with a discussion of the implications for toric surfaces and threefolds.

Fatemeh Mohammadi, Sonja Petrović, Eduardo Sáenz-de-Cabezón

This paper focuses on asymptotic properties of random monomial ideals through a statistical viewpoint. It extends the study of redundancy in monomial ideals by analyzing the poset density of the LCM-lattice. We explore how this density behaves across random algebraic models and structured networks. Experimental data reveal that the LCM-lattice exhibits sharp threshold behavior rather than changing smoothly. We observe a strong negative correlation between the number of generators and LCM-lattice density, abruptly separating three distinct regimes: a low-density Taylor-like regime, a high-density redundant regime, and a narrow transition window. We show that increasing the generator degree causes this density drop to occur at lower probability thresholds. We conclude by conjecturing that for equigenerated squarefree ideals, the LCM-lattice density undergoes a sharp phase transition, analogous to the emergence of giant components in hypergraphs. This suggests that the classical, ideal-by-ideal role of the LCM-lattice as a combinatorial invariant also admits a statistical/asymptotic counterpart: in natural random families, redundancy and resolution-complexity indicators concentrate into distinct typical regimes separated by a narrow transition window.

Fatemeh Mohammadi, Tommaso Romano, Samira Maghool et al.

Collecting high-quality training data is essential for fine-tuning Large Language Models (LLMs). However, acquiring such data is often costly and time-consuming, especially for non-English languages such as Italian. Recently, researchers have begun to explore the use of LLMs to generate synthetic datasets as a viable alternative. This study proposes a pipeline for generating synthetic data and a comprehensive approach for investigating the factors that influence the validity of synthetic data generated by LLMs by examining how model performance is affected by metrics such as prompt strategy, text length and target position in a specific task, i.e. inclusive language detection in Italian job advertisements. Our results show that, in most cases and across different metrics, the fine-tuned models trained on synthetic data consistently outperformed other models on both real and synthetic test datasets. The study discusses the practical implications and limitations of using synthetic data for language detection tasks with LLMs.

Mohammad Derakhshan, Paolo Ceravolo, Fatemeh Mohammadi

This paper investigates the effectiveness of GPT-4o-2024-08-06, one of the Large Language Models (LLM) from OpenAI, in detecting business process anomalies, with a focus on rework anomalies. In our study, we developed a GPT-4o-based tool capable of transforming event logs into a structured format and identifying reworked activities within business event logs. The analysis was performed on a synthetic dataset designed to contain rework anomalies but free of loops. To evaluate the anomaly detection capabilities of GPT 4o-2024-08-06, we used three prompting techniques: zero-shot, one-shot, and few-shot. These techniques were tested on different anomaly distributions, namely normal, uniform, and exponential, to identify the most effective approach for each case. The results demonstrate the strong performance of GPT-4o-2024-08-06. On our dataset, the model achieved 96.14% accuracy with one-shot prompting for the normal distribution, 97.94% accuracy with few-shot prompting for the uniform distribution, and 74.21% accuracy with few-shot prompting for the exponential distribution. These results highlight the model's potential as a reliable tool for detecting rework anomalies in event logs and how anomaly distribution and prompting strategy influence the model's performance.

Fatemeh Mohammadi, Marta Annamaria Tamborini, Paolo Ceravolo et al.

This paper is a collaborative effort between Linguistics, Law, and Computer Science to evaluate stereotypes and biases in automated translation systems. We advocate gender-neutral translation as a means to promote gender inclusion and improve the objectivity of machine translation. Our approach focuses on identifying gender bias in English-to-Italian translations. First, we define gender bias following human rights law and linguistics literature. Then we proceed by identifying gender-specific terms such as she/lei and he/lui as key elements. We then evaluate the cosine similarity between these target terms and others in the dataset to reveal the model's perception of semantic relations. Using numerical features, we effectively evaluate the intensity and direction of the bias. Our findings provide tangible insights for developing and training gender-neutral translation algorithms.