arXiv subjects

Tommaso Di Noia

Publications and source records attributed to Tommaso Di Noia.

At least 37 records · Page 2Linked to original sources

arXiv2026

RUVA: Personalized Transparent On-Device Graph Reasoning

The Personal AI landscape is currently dominated by "Black Box" Retrieval-Augmented Generation. While standard vector databases offer statistical matching, they suffer from a fundamental lack of accountability: when an AI hallucinates or retrieves sensitive data, the user cannot inspect the cause nor correct the error. Worse, "deleting" a concept from a vector space is mathematically imprecise, leaving behind probabilistic "ghosts" that violate true privacy. We propose Ruva, the first "Glass Box" architecture designed for Human-in-the-Loop Memory Curation. Ruva grounds Personal AI in a Personal Knowledge Graph, enabling users to inspect what the AI knows and to perform precise redaction of specific facts. By shifting the paradigm from Vector Matching to Graph Reasoning, Ruva ensures the "Right to be Forgotten." Users are the editors of their own lives; Ruva hands them the pen. The project and the demo video are available at http://sisinf00.poliba.it/ruva/.

cs.AI↗

arXiv2026

A Reproducible and Fair Evaluation of Partition-aware Collaborative Filtering

Similarity-based collaborative filtering (CF) models have long demonstrated strong offline performance and conceptual simplicity. However, their scalability is limited by the quadratic cost of maintaining dense item-item similarity matrices. Partitioning-based paradigms have recently emerged as an effective strategy for balancing effectiveness and efficiency, enabling models to learn local similarities within coherent subgraphs while maintaining a limited global context. In this work, we focus on the Fine-tuning Partition-aware Similarity Refinement (FPSR) framework, a prominent representative of this family, as well as its extension, FPSR+. Reproducible evaluation of partition-aware collaborative filtering remains challenging, as prior FPSR/FPSR+ reports often rely on splits of unclear provenance and omit some similarity-based baselines, thereby complicating fair comparison. We present a transparent, fully reproducible benchmark of FPSR and FPSR+. Based on our results, the family of FPSR models does not consistently perform at the highest level. Overall, it remains competitive, validates its design choices, and shows significant advantages in long-tail scenarios. This highlights the accuracy-coverage trade-offs resulting from partitioning, global components, and hub design. Our investigation clarifies when partition-aware similarity modeling is most beneficial and offers actionable guidance for scalable recommender system design under reproducible protocols.

cs.IR↗

arXiv2026

Exploring Diversity, Novelty, and Popularity Bias in ChatGPT's Recommendations

ChatGPT has emerged as a versatile tool, demonstrating capabilities across diverse domains. Given these successes, the Recommender Systems (RSs) community has begun investigating its applications within recommendation scenarios primarily focusing on accuracy. While the integration of ChatGPT into RSs has garnered significant attention, a comprehensive analysis of its performance across various dimensions remains largely unexplored. Specifically, the capabilities of providing diverse and novel recommendations or exploring potential biases such as popularity bias have not been thoroughly examined. As the use of these models continues to expand, understanding these aspects is crucial for enhancing user satisfaction and achieving long-term personalization. This study investigates the recommendations provided by ChatGPT-3.5 and ChatGPT-4 by assessing ChatGPT's capabilities in terms of diversity, novelty, and popularity bias. We evaluate these models on three distinct datasets and assess their performance in Top-N recommendation and cold-start scenarios. The findings reveal that ChatGPT-4 matches or surpasses traditional recommenders, demonstrating the ability to balance novelty and diversity in recommendations. Furthermore, in the cold-start scenario, ChatGPT models exhibit superior performance in both accuracy and novelty, suggesting they can be particularly beneficial for new users. This research highlights the strengths and limitations of ChatGPT's recommendations, offering new perspectives on the capacity of these models to provide recommendations beyond accuracy-focused metrics.

cs.IR↗

arXiv2026

Exploring Approaches for Detecting Memorization of Recommender System Data in Large Language Models

Large Language Models (LLMs) are increasingly applied in recommendation scenarios due to their strong natural language understanding and generation capabilities. However, they are trained on vast corpora whose contents are not publicly disclosed, raising concerns about data leakage. Recent work has shown that the MovieLens-1M dataset is memorized by both the LLaMA and OpenAI model families, but the extraction of such memorized data has so far relied exclusively on manual prompt engineering. In this paper, we pose three main questions: Is it possible to enhance manual prompting? Can LLM memorization be detected through methods beyond manual prompting? And can the detection of data leakage be automated? To address these questions, we evaluate three approaches: (i) jailbreak prompt engineering; (ii) unsupervised latent knowledge discovery, probing internal activations via Contrast-Consistent Search (CCS) and Cluster-Norm; and (iii) Automatic Prompt Engineering (APE), which frames prompt discovery as a meta-learning process that iteratively refines candidate instructions. Experiments on MovieLens-1M using LLaMA models show that jailbreak prompting does not improve the retrieval of memorized items and remains inconsistent; CCS reliably distinguishes genuine from fabricated movie titles but fails on numerical user and rating data; and APE retrieves item-level information with moderate success yet struggles to recover numerical interactions. These findings suggest that automatically optimizing prompts is the most promising strategy for extracting memorized samples.

cs.IR↗

arXiv2025

GradeSQL: Test-Time Inference with Outcome Reward Models for Text-to-SQL Generation from Large Language Models

Text-to-SQL, the task of translating natural language questions into SQL queries, has significantly advanced with the introduction of Large Language Models (LLMs), broadening database accessibility for a wide range of users. Despite substantial progress in generating valid SQL, current LLMs still struggle with complex queries. To address this limitation, test-time strategies such as Best-of-N (BoN) and Majority Voting (Maj) are often employed, based on the assumption that LLMs can produce correct answers after multiple attempts. However, these methods rely on surface-level heuristics, selecting the syntactically correct query through execution-based BoN (ex-BoN) or the most frequently generated one through Majority Voting. Recently, Outcome Reward Models (ORMs), which assign utility scores to generated outputs based on semantic correctness, have emerged as a promising reinforcement learning approach for improving model alignment. We argue that ORMs could serve as an effective new test-time heuristic, although their application in this context remains largely underexplored. In this work, we propose a unified framework for training ORMs tailored to the Text-to-SQL task and assess their effectiveness as a test-time heuristic within the BoN strategy. We benchmark ORMs against ex-BoN and Maj across the BIRD and Spider datasets, fine-tuning diverse open-source LLMs from the Qwen2, Granite3, and Llama3 families. Results show that ORMs outperform ex-BoN and Maj, achieving execution accuracy gains of +4.33% (BIRD) and +2.10% (Spider) over ex-BoN, and +2.91% (BIRD) and +0.93% (Spider) over Maj. We further demonstrate that finetuning models already aligned with SQL generation, such as OmniSQL, yields superior ORM performance. Additionally, we observe that ORMs achieve competitive results on simple queries and benefit more from an increased number of candidates compared to ex-BoN and Maj.

cs.AI↗

arXiv2025

Type-Less yet Type-Aware Inductive Link Prediction with Pretrained Language Models

Inductive link prediction is emerging as a key paradigm for real-world knowledge graphs (KGs), where new entities frequently appear and models must generalize to them without retraining. Predicting links in a KG faces the challenge of guessing previously unseen entities by leveraging generalizable node features such as subgraph structure, type annotations, and ontological constraints. However, explicit type information is often lacking or incomplete. Even when available, type information in most KGs is often coarse-grained, sparse, and prone to errors due to human annotation. In this work, we explore the potential of pre-trained language models (PLMs) to enrich node representations with implicit type signals. We introduce TyleR, a Type-less yet type-awaRe approach for subgraph-based inductive link prediction that leverages PLMs for semantic enrichment. Experiments on standard benchmarks demonstrate that TyleR outperforms state-of-the-art baselines in scenarios with scarce type annotations and sparse graph connectivity. To ensure reproducibility, we share our code at https://github.com/sisinflab/tyler .

cs.CL↗

arXiv2025

Balancing Accuracy and Novelty with Sub-Item Popularity

In the realm of music recommendation, sequential recommenders have shown promise in capturing the dynamic nature of music consumption. A key characteristic of this domain is repetitive listening, where users frequently replay familiar tracks. To capture these repetition patterns, recent research has introduced Personalised Popularity Scores (PPS), which quantify user-specific preferences based on historical frequency. While PPS enhances relevance in recommendation, it often reinforces already-known content, limiting the system's ability to surface novel or serendipitous items - key elements for fostering long-term user engagement and satisfaction. To address this limitation, we build upon RecJPQ, a Transformer-based framework initially developed to improve scalability in large-item catalogues through sub-item decomposition. We repurpose RecJPQ's sub-item architecture to model personalised popularity at a finer granularity. This allows us to capture shared repetition patterns across sub-embeddings - latent structures not accessible through item-level popularity alone. We propose a novel integration of sub-ID-level personalised popularity within the RecJPQ framework, enabling explicit control over the trade-off between accuracy and personalised novelty. Our sub-ID-level PPS method (sPPS) consistently outperforms item-level PPS by achieving significantly higher personalised novelty without compromising recommendation accuracy. Code and experiments are publicly available at https://github.com/sisinflab/Sub-id-Popularity.

cs.IR↗

arXiv2025

ViLLA-MMBench: A Unified Benchmark Suite for LLM-Augmented Multimodal Movie Recommendation

Recommending long-form video content demands joint modeling of visual, audio, and textual modalities, yet most benchmarks address only raw features or narrow fusion. We present ViLLA-MMBench, a reproducible, extensible benchmark for LLM-augmented multimodal movie recommendation. Built on MovieLens and MMTF-14K, it aligns dense item embeddings from three modalities: audio (block-level, i-vector), visual (CNN, AVF), and text. Missing or sparse metadata is automatically enriched using state-of-the-art LLMs (e.g., OpenAI Ada), generating high-quality synopses for thousands of movies. All text (raw or augmented) is embedded with configurable encoders (Ada, LLaMA-2, Sentence-T5), producing multiple ready-to-use sets. The pipeline supports interchangeable early-, mid-, and late-fusion (concatenation, PCA, CCA, rank-aggregation) and multiple backbones (MF, VAECF, VBPR, AMR, VMF) for ablation. Experiments are fully declarative via a single YAML file. Evaluation spans accuracy (Recall, nDCG) and beyond-accuracy metrics: cold-start rate, coverage, novelty, diversity, fairness. Results show LLM-based augmentation and strong text embeddings boost cold-start and coverage, especially when fused with audio-visual features. Systematic benchmarking reveals universal versus backbone- or metric-specific combinations. Open-source code, embeddings, and configs enable reproducible, fair multimodal RS research and advance principled generative AI integration in large-scale recommendation. Code: https://recsys-lab.github.io/ViLLA-MMBench

cs.IR↗

arXiv2025

Do Recommender Systems Really Leverage Multimodal Content? A Comprehensive Analysis on Multimodal Representations for Recommendation

Multimodal Recommender Systems aim to improve recommendation accuracy by integrating heterogeneous content, such as images and textual metadata. While effective, it remains unclear whether their gains stem from true multimodal understanding or increased model complexity. This work investigates the role of multimodal item embeddings, emphasizing the semantic informativeness of the representations. Initial experiments reveal that embeddings from standard extractors (e.g., ResNet50, Sentence-Bert) enhance performance, but rely on modality-specific encoders and ad hoc fusion strategies that lack control over cross-modal alignment. To overcome these limitations, we leverage Large Vision-Language Models (LVLMs) to generate multimodal-by-design embeddings via structured prompts. This approach yields semantically aligned representations without requiring any fusion. Experiments across multiple settings show notable performance improvements. Furthermore, LVLMs embeddings offer a distinctive advantage: they can be decoded into structured textual descriptions, enabling direct assessment of their multimodal comprehension. When such descriptions are incorporated as side content into recommender systems, they improve recommendation performance, empirically validating the semantic depth and alignment encoded within LVLMs outputs. Our study highlights the importance of semantically rich representations and positions LVLMs as a compelling foundation for building robust and meaningful multimodal representations in recommendation tasks.

cs.IR↗

arXiv2025

XAI4LLM. Let Machine Learning Models and LLMs Collaborate for Enhanced In-Context Learning in Healthcare

Clinical decision support systems require models that are not only highly accurate but also equitable and sensitive to the implications of missed diagnoses. In this study, we introduce a knowledge-guided in-context learning (ICL) framework designed to enable large language models (LLMs) to effectively process structured clinical data. Our approach integrates domain-specific feature groupings, carefully balanced few-shot examples, and task-specific prompting strategies. We systematically evaluate this method across seventy distinct ICL designs by various prompt variations and two different communication styles-natural-language narrative and numeric conversational-and compare its performance to robust classical machine learning (ML) benchmarks on tasks involving heart disease and diabetes prediction. Our findings indicate that while traditional ML models maintain superior performance in balanced precision-recall scenarios, LLMs employing narrative prompts with integrated domain knowledge achieve higher recall and significantly reduce gender bias, effectively narrowing fairness disparities by an order of magnitude. Despite the current limitation of increased inference latency, LLMs provide notable advantages, including the capacity for zero-shot deployment and enhanced equity. This research offers the first comprehensive analysis of ICL design considerations for applying LLMs to tabular clinical tasks and highlights distillation and multimodal extensions as promising directions for future research.

cs.LG↗

arXiv2025

Do We Really Need Specialization? Evaluating Generalist Text Embeddings for Zero-Shot Recommendation and Search

Pre-trained language models (PLMs) are widely used to derive semantic representations from item metadata in recommendation and search. In sequential recommendation, PLMs enhance ID-based embeddings through textual metadata, while in product search, they align item characteristics with user intent. Recent studies suggest task and domain-specific fine-tuning are needed to improve representational power. This paper challenges this assumption, showing that Generalist Text Embedding Models (GTEs), pre-trained on large-scale corpora, can guarantee strong zero-shot performance without specialized adaptation. Our experiments demonstrate that GTEs outperform traditional and fine-tuned models in both sequential recommendation and product search. We attribute this to a superior representational power, as they distribute features more evenly across the embedding space. Finally, we show that compressing embedding dimensions by focusing on the most informative directions (e.g., via PCA) effectively reduces noise and improves the performance of specialized models. To ensure reproducibility, we provide our repository at https://split.to/gte4ps.

cs.IR↗

arXiv2025

LLaMAs Have Feelings Too: Unveiling Sentiment and Emotion Representations in LLaMA Models Through Probing

Large Language Models (LLMs) have rapidly become central to NLP, demonstrating their ability to adapt to various tasks through prompting techniques, including sentiment analysis. However, we still have a limited understanding of how these models capture sentiment-related information. This study probes the hidden layers of Llama models to pinpoint where sentiment features are most represented and to assess how this affects sentiment analysis. Using probe classifiers, we analyze sentiment encoding across layers and scales, identifying the layers and pooling methods that best capture sentiment signals. Our results show that sentiment information is most concentrated in mid-layers for binary polarity tasks, with detection accuracy increasing up to 14% over prompting techniques. Additionally, we find that in decoder-only models, the last token is not consistently the most informative for sentiment encoding. Finally, this approach enables sentiment tasks to be performed with memory requirements reduced by an average of 57%. These insights contribute to a broader understanding of sentiment in LLMs, suggesting layer-specific probing as an effective approach for sentiment tasks beyond prompting, with potential to enhance model utility and reduce memory requirements.

cs.CL↗

arXiv2025

Are the Hidden States Hiding Something? Testing the Limits of Factuality-Encoding Capabilities in LLMs

Factual hallucinations are a major challenge for Large Language Models (LLMs). They undermine reliability and user trust by generating inaccurate or fabricated content. Recent studies suggest that when generating false statements, the internal states of LLMs encode information about truthfulness. However, these studies often rely on synthetic datasets that lack realism, which limits generalization when evaluating the factual accuracy of text generated by the model itself. In this paper, we challenge the findings of previous work by investigating truthfulness encoding capabilities, leading to the generation of a more realistic and challenging dataset. Specifically, we extend previous work by introducing: (1) a strategy for sampling plausible true-false factoid sentences from tabular data and (2) a procedure for generating realistic, LLM-dependent true-false datasets from Question Answering collections. Our analysis of two open-source LLMs reveals that while the findings from previous studies are partially validated, generalization to LLM-generated datasets remains challenging. This study lays the groundwork for future research on factuality in LLMs and offers practical guidelines for more effective evaluation.

cs.CL↗

arXiv2025

Do LLMs Memorize Recommendation Datasets? A Preliminary Study on MovieLens-1M

Large Language Models (LLMs) have become increasingly central to recommendation scenarios due to their remarkable natural language understanding and generation capabilities. Although significant research has explored the use of LLMs for various recommendation tasks, little effort has been dedicated to verifying whether they have memorized public recommendation dataset as part of their training data. This is undesirable because memorization reduces the generalizability of research findings, as benchmarking on memorized datasets does not guarantee generalization to unseen datasets. Furthermore, memorization can amplify biases, for example, some popular items may be recommended more frequently than others. In this work, we investigate whether LLMs have memorized public recommendation datasets. Specifically, we examine two model families (GPT and Llama) across multiple sizes, focusing on one of the most widely used dataset in recommender systems: MovieLens-1M. First, we define dataset memorization as the extent to which item attributes, user profiles, and user-item interactions can be retrieved by prompting the LLMs. Second, we analyze the impact of memorization on recommendation performance. Lastly, we examine whether memorization varies across model families and model sizes. Our results reveal that all models exhibit some degree of memorization of MovieLens-1M, and that recommendation performance is related to the extent of memorization. We have made all the code publicly available at: https://github.com/sisinflab/LLM-MemoryInspector

cs.IR↗

arXiv2025

Stealthy LLM-Driven Data Poisoning Attacks Against Embedding-Based Retrieval-Augmented Recommender Systems

We present a systematic study of provider-side data poisoning in retrieval-augmented recommender systems (RAG-based). By modifying only a small fraction of tokens within item descriptions -- for instance, adding emotional keywords or borrowing phrases from semantically related items -- an attacker can significantly promote or demote targeted items. We formalize these attacks under token-edit and semantic-similarity constraints, and we examine their effectiveness in both promotion (long-tail items) and demotion (short-head items) scenarios. Our experiments on MovieLens, using two large language model (LLM) retrieval modules, show that even subtle attacks shift final rankings and item exposures while eluding naive detection. The results underscore the vulnerability of RAG-based pipelines to small-scale metadata rewrites and emphasize the need for robust textual consistency checks and provenance tracking to thwart stealthy provider-side poisoning.

cs.IR↗

arXiv2025

De-centering the (Traditional) User: Multistakeholder Evaluation of Recommender Systems

Multistakeholder recommender systems are those that account for the impacts and preferences of multiple groups of individuals, not just the end users receiving recommendations. Due to their complexity, these systems cannot be evaluated strictly by the overall utility of a single stakeholder, as is often the case of more mainstream recommender system applications. In this article, we focus our discussion on the challenges of multistakeholder evaluation of recommender systems. We bring attention to the different aspects involved -- from the range of stakeholders involved (including but not limited to providers and consumers) to the values and specific goals of each relevant stakeholder. We discuss how to move from theoretical principles to practical implementation, providing specific use case examples. Finally, we outline open research directions for the RecSys community to explore. We aim to provide guidance to researchers and practitioners about incorporating these complex and domain-dependent issues of evaluation in the course of designing, developing, and researching applications with multistakeholder aspects.

cs.IR↗

arXiv2025

DataRec: A Python Library for Standardized and Reproducible Data Management in Recommender Systems

Recommender systems have demonstrated significant impact across diverse domains, yet ensuring the reproducibility of experimental findings remains a persistent challenge. A primary obstacle lies in the fragmented and often opaque data management strategies employed during the preprocessing stage, where decisions about dataset selection, filtering, and splitting can substantially influence outcomes. To address these limitations, we introduce DataRec, an open-source Python-based library specifically designed to unify and streamline data handling in recommender system research. By providing reproducible routines for dataset preparation, data versioning, and seamless integration with other frameworks, DataRec promotes methodological standardization, interoperability, and comparability across different experimental setups. Our design is informed by an in-depth review of 55 state-of-the-art recommendation studies ensuring that DataRec adopts best practices while addressing common pitfalls in data management. Ultimately, our contribution facilitates fair benchmarking, enhances reproducibility, and fosters greater trust in experimental results within the broader recommender systems community. The DataRec library, documentation, and examples are freely available at https://github.com/sisinflab/DataRec.

cs.IR↗

arXiv2025

AirTOWN: A Privacy-Preserving Mobile App for Real-time Pollution-Aware POI Suggestion

This demo paper presents \airtown, a privacy-preserving mobile application that provides real-time, pollution-aware recommendations for points of interest (POIs) in urban environments. By combining real-time Air Quality Index (AQI) data with user preferences, the proposed system aims to help users make health-conscious decisions about the locations they visit. The application utilizes collaborative filtering for personalized suggestions, and federated learning for privacy protection, and integrates AQI data from sensor networks in cities such as Bari, Italy, and Cork, UK. In areas with sparse sensor coverage, interpolation techniques approximate AQI values, ensuring broad applicability. This system offers a poromsing, health-oriented POI recommendation solution that adapts dynamically to current urban air quality conditions while safeguarding user privacy.

cs.IR↗