arXiv subjects

Simone Paolo Ponzetto

Publications and source records attributed to Simone Paolo Ponzetto.

At least 19 recordsLinked to original sources

arXiv2026

The Multilingual FrameNet Corpus

This paper introduces the Multilingual FrameNet Corpus (mFNC), a novel resource that extends the English Berkeley FrameNet corpus by collecting and harmonizing existing language-specific corpora across nine additional languages: Brazilian Portuguese, Chinese, Dutch, French, German, Italian, Korean, Latvian and Swedish. By training models that rely on different architectures on the mFNC, we consistently outperform existing state-of-the-art Frame Semantic Parsers in both multilingual and cross-lingual settings, underscoring the importance of multilingual training data. The mFNC and our trained FSP models are openly available at https://github.com/beatrice-f/mFNC.

cs.CL↗

arXiv2026

Mood Matters: How Syntactic Sensitivity Undermines Safety Alignment

Large language models typically undergo post-training to align them with safety policies but there exist many sophisticated jailbreaks that sidestep established safeguards. For instance, prior work by Andriushchenko et al. (2025) has found that changing the grammatical tense from present to past can be enough to elicit harmful responses. In this work, we uncover a more general failure of non-imperative syntactic forms. We demonstrate that this syntactic vulnerability exists in 16 models up to 70B parameters, using behavioral evaluation. To investigate the root cause, we apply causal mediation analysis, finding that refusal is partially conditioned on upstream syntactic features. By steering these purely syntactic features we are able to trigger and suppress refusal. Finally, we trace this ill-conditioning to linguistically biased post-training data of open-source models and show that increasing syntactic diversity can mitigate the issue. Our findings suggest that current alignment approaches introduce confounders that prevent a pure semantic grounding of the refusal decision.

cs.CL↗

arXiv2026

ChronoLens: Measuring Language Change Across Time, Languages, and Linguistic Levels

Historical language change affects morphology, syntax, semantics, and pragmatics, yet computational studies typically examine these levels with incompatible representations and therefore cannot determine whether they evolve together across languages. We address this problem by asking how the magnitude and direction of change vary across linguistic levels, languages, and historical periods within a single analytical space. We introduce ChronoLens, a framework that combines frozen multilingual language models, feature-aligned crosscoders, and post-hoc linguistic interventions, and apply it to 44.98 million documents and approximately 17.2 billion tokens from five parliamentary traditions spanning 1803--2026. The resulting sparse representations agree substantially more strongly with linguistic statistics than dense embeddings or a pooled sparse autoencoder ($ρ=0.72$ versus $0.29$ and $0.28$), and reveal that morphology, syntax, semantics, and pragmatics generally change by comparable amounts within a language, while languages differ markedly in when, how far, and in which direction they change. These findings show that historical language change is a structured, multidimensional process: similar magnitudes can conceal different trajectories, and meaningful cross-linguistic comparison requires measuring both distance and direction.

cs.CL↗

arXiv2026

To MRL or not to MRL: Text Embeddings are Robust to Truncation Without Matryoshka Learning, Except In Heavy Truncation Scenarios

Matryoshka Representation Learning (MRL) is a widely adopted approach for training text encoders so they provide useful text representations at various sizes, available by simply truncating the resulting vectors at sizes pre-determined at training time. Recent works have shown that randomly truncating text embeddings has minimal impact in downstream performance unless vectors are reduced in size by at least 70%, suggesting that embeddings are already robust to truncation without the use of MRL. However, no prior work has compared random truncation to MRL, so it is unclear how the two methods compare as effective embedding reduction methods. In this paper, we study this by applying the same truncation used by MRL to models trained with and without MRL. Our results across several models and downstream tasks show that, unless heavily truncating embeddings (i.e. reducing their size by at least 80%), truncated embeddings of non-MRL models are competitive with, and often outperform models trained with MRL. This suggests that truncation robustness may not necessarily come from MRL, and that the choice of spending the additional training cost of MRL depends on whether heavy truncation is desired. We make our code available for reproduction.

cs.LG↗

arXiv2026

Beyond Reproduction: A Paired-Task Framework for Assessing LLM Comprehension and Creativity in Literary Translation

Large language models (LLMs) are increasingly used for creative tasks such as literary translation. Yet translational creativity remains underexplored and is rarely evaluated at scale, while source-text comprehension is typically studied in isolation, despite the fact that, in professional translation, comprehension and creativity are tightly intertwined. We address these gaps with a paired-task framework applied to literary excerpts from 11 books. Task 1 assesses source-text comprehension, and Task 2 evaluates translational creativity through Units of Creative Potential (UCPs), such as metaphors and wordplay. Using a scalable evaluation setup that combines expert human annotations with UCP-based automatic scoring, we benchmark 23 models and four creativity-oriented prompts. Our findings show that strong comprehension does not translate into human-level creativity: models often produce literal or contextually inappropriate renderings, with particularly large gaps for the more distant English-Chinese language pair. Creativity-oriented prompts yield only modest gains, and only one model, Mistral-Large, comes close to human-level creativity (0.167 vs. 0.246). Across all model-prompt combinations, only three exceed a creativity score of 0.1, while the rest remain at or near zero.

cs.CL↗

arXiv2026

Shiny Stories, Hidden Struggles: Investigating the Representation of Disability Through the Lens of LLMs

Modern Large Language Models (LLMs) have recently attracted much attention for their ability to simulate human behavior and generate text that reflects personas and demographic groups. While these capabilities can open up a multitude of diverse applications across fields, it is crucial to examine how such models represent various target groups since LLMs can perpetuate and amplify biases or discrimination against historically marginalized communities or, alternatively, as a result of debiasing efforts, overcorrect by portraying overly positive stereotypes. This overcompensation can idealize these groups, erasing the complexities and challenges they face in favor of unrealistic depictions. In this paper, we investigate how LLMs represent disability by simulating the perspectives of individuals with disabilities in generating social media posts. These posts are then compared with those written by real people with disabilities, focusing on emotional tone, sentiment, and representative words and themes. Our analysis reveals two key findings: (1) LLMs often idealize the experiences of people with disabilities, producing overly positive stereotypes that, despite appearing uplifting, fail to authentically capture their lived realities; and (2) a comparative analysis of posts simulating individuals with and without disabilities highlights a negative bias, where certain topics, such as career and entertainment, are disproportionately associated with nondisabled individuals. This reinforces exclusionary narratives and over-idealized portrayals of disability, misrepresenting the actual challenges faced by this community. These findings align with broader concerns and ongoing research showing that LLMs struggle to reflect the diverse realities of society, particularly the nuanced experiences of marginalized groups, and underscore the need for critical scrutiny of their representations.

cs.CL↗

arXiv2025

Randomly Removing 50% of Dimensions in Text Embeddings has Minimal Impact on Retrieval and Classification Tasks

In this paper, we study the surprising impact that truncating text embeddings has on downstream performance. We consistently observe across 6 state-of-the-art text encoders and 26 downstream tasks, that randomly removing up to 50% of embedding dimensions results in only a minor drop in performance, less than 10%, in retrieval and classification tasks. Given the benefits of using smaller-sized embeddings, as well as the potential insights about text encoding, we study this phenomenon and find that, contrary to what is suggested in prior work, this is not the result of an ineffective use of representation space. Instead, we find that a large number of uniformly distributed dimensions actually cause an increase in performance when removed. This would explain why, on average, removing a large number of embedding dimensions results in a marginal drop in performance. We make similar observations when truncating the embeddings used by large language models to make next-token predictions on generative tasks, suggesting that this phenomenon is not isolated to classification or retrieval tasks.

cs.LG↗

arXiv2025

GUISpector: An MLLM Agent Framework for Automated Verification of Natural Language Requirements in GUI Prototypes

GUIs are foundational to interactive systems and play a pivotal role in early requirements elicitation through prototyping. Ensuring that GUI implementations fulfill NL requirements is essential for robust software engineering, especially as LLM-driven programming agents become increasingly integrated into development workflows. Existing GUI testing approaches, whether traditional or LLM-driven, often fall short in handling the complexity of modern interfaces, and typically lack actionable feedback and effective integration with automated development agents. In this paper, we introduce GUISpector, a novel framework that leverages a multi-modal (M)LLM-based agent for the automated verification of NL requirements in GUI prototypes. First, GUISpector adapts a MLLM agent to interpret and operationalize NL requirements, enabling to autonomously plan and execute verification trajectories across GUI applications. Second, GUISpector systematically extracts detailed NL feedback from the agent's verification process, providing developers with actionable insights that can be used to iteratively refine the GUI artifact or directly inform LLM-based code generation in a closed feedback loop. Third, we present an integrated tool that unifies these capabilities, offering practitioners an accessible interface for supervising verification runs, inspecting agent rationales and managing the end-to-end requirements verification process. We evaluated GUISpector on a comprehensive set of 150 requirements based on 900 acceptance criteria annotations across diverse GUI applications, demonstrating effective detection of requirement satisfaction and violations and highlighting its potential for seamless integration of actionable feedback into automated LLM-driven development workflows. The video presentation of GUISpector is available at: https://youtu.be/JByYF6BNQeE, showcasing its main capabilities.

cs.SE↗

arXiv2025

TikZero: Zero-Shot Text-Guided Graphics Program Synthesis

Automatically synthesizing figures from text captions is a compelling capability. However, achieving high geometric precision and editability requires representing figures as graphics programs in languages like TikZ, and aligned training data (i.e., graphics programs with captions) remains scarce. Meanwhile, large amounts of unaligned graphics programs and captioned raster images are more readily available. We reconcile these disparate data sources by presenting TikZero, which decouples graphics program generation from text understanding by using image representations as an intermediary bridge. It enables independent training on graphics programs and captioned images and allows for zero-shot text-guided graphics program synthesis during inference. We show that our method substantially outperforms baselines that can only operate with caption-aligned graphics programs. Furthermore, when leveraging caption-aligned graphics programs as a complementary training signal, TikZero matches or exceeds the performance of much larger models, including commercial systems like GPT-4o. Our code, datasets, and select models are publicly available.

cs.CL↗

arXiv2025

GUI-ReRank: Enhancing GUI Retrieval with Multi-Modal LLM-based Reranking

GUI prototyping is a fundamental component in the development of modern interactive systems, which are now ubiquitous across diverse application domains. GUI prototypes play a critical role in requirements elicitation by enabling stakeholders to visualize, assess, and refine system concepts collaboratively. Moreover, prototypes serve as effective tools for early testing, iterative evaluation, and validation of design ideas with both end users and development teams. Despite these advantages, the process of constructing GUI prototypes remains resource-intensive and time-consuming, frequently demanding substantial effort and expertise. Recent research has sought to alleviate this burden through NL-based GUI retrieval approaches, which typically rely on embedding-based retrieval or tailored ranking models for specific GUI repositories. However, these methods often suffer from limited retrieval performance and struggle to generalize across arbitrary GUI datasets. In this work, we present GUI-ReRank, a novel framework that integrates rapid embedding-based constrained retrieval models with highly effective MLLM-based reranking techniques. GUI-ReRank further introduces a fully customizable GUI repository annotation and embedding pipeline, enabling users to effortlessly make their own GUI repositories searchable, which allows for rapid discovery of relevant GUIs for inspiration or seamless integration into customized LLM-based RAG workflows. We evaluated our approach on an established NL-based GUI retrieval benchmark, demonstrating that GUI-ReRank significantly outperforms SOTA tailored LTR models in both retrieval accuracy and generalizability. Additionally, we conducted a comprehensive cost and efficiency analysis of employing MLLMs for reranking, providing valuable insights regarding the trade-offs between retrieval effectiveness and computational resources. Video: https://youtu.be/_7x9UCh82ug

cs.SE↗

arXiv2025

GUIDE: LLM-Driven GUI Generation Decomposition for Automated Prototyping

GUI prototyping serves as one of the most valuable techniques for enhancing the elicitation of requirements and facilitating the visualization and refinement of customer needs. While GUI prototyping has a positive impact on the software development process, it simultaneously demands significant effort and resources. The emergence of Large Language Models (LLMs) with their impressive code generation capabilities offers a promising approach for automating GUI prototyping. Despite their potential, there is a gap between current LLM-based prototyping solutions and traditional user-based GUI prototyping approaches which provide visual representations of the GUI prototypes and direct editing functionality. In contrast, LLMs and related generative approaches merely produce text sequences or non-editable image output, which lacks both mentioned aspects and therefore impede supporting GUI prototyping. Moreover, minor changes requested by the user typically lead to an inefficient regeneration of the entire GUI prototype when using LLMs directly. In this work, we propose GUIDE, a novel LLM-driven GUI generation decomposition approach seamlessly integrated into the popular prototyping framework Figma. Our approach initially decomposes high-level GUI descriptions into fine-granular GUI requirements, which are subsequently translated into Material Design GUI prototypes, enabling higher controllability and more efficient adaption of changes. To efficiently conduct prompting-based generation of Material Design GUI prototypes, we propose a retrieval-augmented generation approach to integrate the component library. Our preliminary evaluation demonstrates the effectiveness of GUIDE in bridging the gap between LLM generation capabilities and traditional GUI prototyping workflows, offering a more effective and controlled user-based approach to LLM-driven GUI prototyping. Video: https://youtu.be/C9RbhMxqpTU

cs.SE↗

arXiv2025

Do LLMs Dream of Ontologies?

Large Language Models (LLMs) have demonstrated remarkable performance across diverse natural language processing tasks, yet their ability to memorize structured knowledge remains underexplored. In this paper, we investigate the extent to which general-purpose pre-trained LLMs retain and correctly reproduce concept identifier (ID)-label associations from publicly available ontologies. We conduct a systematic evaluation across multiple ontological resources, including the Gene Ontology, Uberon, Wikidata, and ICD-10, using LLMs such as Pythia-12B, Gemini-1.5-Flash, GPT-3.5, and GPT-4. Our findings reveal that only a small fraction of ontological concepts is accurately memorized, with GPT-4 demonstrating the highest performance. To understand why certain concepts are memorized more effectively than others, we analyze the relationship between memorization accuracy and concept popularity on the Web. Our results indicate a strong correlation between the frequency of a concept's occurrence online and the likelihood of accurately retrieving its ID from the label. This suggests that LLMs primarily acquire such knowledge through indirect textual exposure rather than directly from structured ontological resources. Furthermore, we introduce new metrics to quantify prediction invariance, demonstrating that the stability of model responses across variations in prompt language and temperature settings can serve as a proxy for estimating memorization robustness.

cs.CL↗

arXiv2024

Enriching Social Science Research via Survey Item Linking

Questions within surveys, called survey items, are used in the social sciences to study latent concepts, such as the factors influencing life satisfaction. Instead of using explicit citations, researchers paraphrase the content of the survey items they use in-text. However, this makes it challenging to find survey items of interest when comparing related work. Automatically parsing and linking these implicit mentions to survey items in a knowledge base can provide more fine-grained references. We model this task, called Survey Item Linking (SIL), in two stages: mention detection and entity disambiguation. Due to an imprecise definition of the task, existing datasets used for evaluating the performance for SIL are too small and of low-quality. We argue that latent concepts and survey item mentions should be differentiated. To this end, we create a high-quality and richly annotated dataset consisting of 20,454 English and German sentences. By benchmarking deep learning systems for each of the two stages independently and sequentially, we demonstrate that the task is feasible, but observe that errors propagate from the first stage, leading to a lower overall task performance. Moreover, mentions that require the context of multiple sentences are more challenging to identify for models in the first stage. Modeling the entire context of a document and combining the two stages into an end-to-end system could mitigate these problems in future work, and errors could additionally be reduced by collecting more diverse data and by improving the quality of the knowledge base. The data and code are available at https://github.com/e-tornike/SIL .

cs.DL↗

arXiv2024

Zero-Shot Prompting Approaches for LLM-based Graphical User Interface Generation

Graphical user interface (GUI) prototyping represents an essential activity in the development of interactive systems, which are omnipresent today. GUI prototypes facilitate elicitation of requirements and help to test, evaluate, and validate ideas with users and the development team. However, creating GUI prototypes is a time-consuming process and often requires extensive resources. While existing research for automatic GUI generation focused largely on resource-intensive training and fine-tuning of LLMs, mainly for low-fidelity GUIs, we investigate the potential and effectiveness of Zero-Shot (ZS) prompting for high-fidelity GUI generation. We propose a Retrieval-Augmented GUI Generation (RAGG) approach, integrated with an LLM-based GUI retrieval re-ranking and filtering mechanism based on a large-scale GUI repository. In addition, we adapt Prompt Decomposition (PDGG) and Self-Critique (SCGG) for GUI generation. To evaluate the effectiveness of the proposed ZS prompting approaches for GUI generation, we extensively evaluated the accuracy and subjective satisfaction of the generated GUI prototypes. Our evaluation, which encompasses over 3,000 GUI annotations from over 100 crowd-workers with UI/UX experience, shows that SCGG, in contrast to PDGG and RAGG, can lead to more effective GUI generation, and provides valuable insights into the defects that are produced by the LLMs in the generated GUI prototypes.

cs.SE↗

arXiv2024

ScImage: How Good Are Multimodal Large Language Models at Scientific Text-to-Image Generation?

Multimodal large language models (LLMs) have demonstrated impressive capabilities in generating high-quality images from textual instructions. However, their performance in generating scientific images--a critical application for accelerating scientific progress--remains underexplored. In this work, we address this gap by introducing ScImage, a benchmark designed to evaluate the multimodal capabilities of LLMs in generating scientific images from textual descriptions. ScImage assesses three key dimensions of understanding: spatial, numeric, and attribute comprehension, as well as their combinations, focusing on the relationships between scientific objects (e.g., squares, circles). We evaluate five models, GPT-4o, Llama, AutomaTikZ, Dall-E, and StableDiffusion, using two modes of output generation: code-based outputs (Python, TikZ) and direct raster image generation. Additionally, we examine four different input languages: English, German, Farsi, and Chinese. Our evaluation, conducted with 11 scientists across three criteria (correctness, relevance, and scientific accuracy), reveals that while GPT-4o produces outputs of decent quality for simpler prompts involving individual dimensions such as spatial, numeric, or attribute understanding in isolation, all models face challenges in this task, especially for more complex prompts.

cs.AI↗

arXiv2024

DeTikZify: Synthesizing Graphics Programs for Scientific Figures and Sketches with TikZ

Creating high-quality scientific figures can be time-consuming and challenging, even though sketching ideas on paper is relatively easy. Furthermore, recreating existing figures that are not stored in formats preserving semantic information is equally complex. To tackle this problem, we introduce DeTikZify, a novel multimodal language model that automatically synthesizes scientific figures as semantics-preserving TikZ graphics programs based on sketches and existing figures. To achieve this, we create three new datasets: DaTikZv2, the largest TikZ dataset to date, containing over 360k human-created TikZ graphics; SketchFig, a dataset that pairs hand-drawn sketches with their corresponding scientific figures; and MetaFig, a collection of diverse scientific figures and associated metadata. We train DeTikZify on MetaFig and DaTikZv2, along with synthetically generated sketches learned from SketchFig. We also introduce an MCTS-based inference algorithm that enables DeTikZify to iteratively refine its outputs without the need for additional training. Through both automatic and human evaluation, we demonstrate that DeTikZify outperforms commercial Claude 3 and GPT-4V in synthesizing TikZ programs, with the MCTS algorithm effectively boosting its performance. We make our code, models, and datasets publicly available.

cs.CL↗

arXiv2024

Self-Elicitation of Requirements with Automated GUI Prototyping

Requirements Elicitation (RE) is a crucial activity especially in the early stages of software development. GUI prototyping has widely been adopted as one of the most effective RE techniques for user-facing software systems. However, GUI prototyping requires (i) the availability of experienced requirements analysts, (ii) typically necessitates conducting multiple joint sessions with customers and (iii) creates considerable manual effort. In this work, we propose SERGUI, a novel approach enabling the Self-Elicitation of Requirements (SER) based on an automated GUI prototyping assistant. SERGUI exploits the vast prototyping knowledge embodied in a large-scale GUI repository through Natural Language Requirements (NLR) based GUI retrieval and facilitates fast feedback through GUI prototypes. The GUI retrieval approach is closely integrated with a Large Language Model (LLM) driving the prompting-based recommendation of GUI features for the current GUI prototyping context and thus stimulating the elicitation of additional requirements. We envision SERGUI to be employed in the initial RE phase, creating an initial GUI prototype specification to be used by the analyst as a means for communicating the requirements. To measure the effectiveness of our approach, we conducted a preliminary evaluation. Video presentation of SERGUI at: https://youtu.be/pzAAB9Uht80

cs.SE↗

arXiv2024

Interlinking User Stories and GUI Prototyping: A Semi-Automatic LLM-based Approach

Interactive systems are omnipresent today and the need to create graphical user interfaces (GUIs) is just as ubiquitous. For the elicitation and validation of requirements, GUI prototyping is a well-known and effective technique, typically employed after gathering initial user requirements represented in natural language (NL) (e.g., in the form of user stories). Unfortunately, GUI prototyping often requires extensive resources, resulting in a costly and time-consuming process. Despite various easy-to-use prototyping tools in practice, there is often a lack of adequate resources for developing GUI prototypes based on given user requirements. In this work, we present a novel Large Language Model (LLM)-based approach providing assistance for validating the implementation of functional NL-based requirements in a GUI prototype embedded in a prototyping tool. In particular, our approach aims to detect functional user stories that are not implemented in a GUI prototype and provides recommendations for suitable GUI components directly implementing the requirements. We collected requirements for existing GUIs in the form of user stories and evaluated our proposed validation and recommendation approach with this dataset. The obtained results are promising for user story validation and we demonstrate feasibility for the GUI component recommendations.

cs.SE↗