arXiv subjects

Riccardo Cantini

Publications and source records attributed to Riccardo Cantini.

7 recordsLinked to original sources

arXiv2026

ClinAgent: A ReAct-Based Agent for Conversational Access to Clinical Trial Information

Querying clinical trial registries remains a manual and error-prone process, requiring researchers to navigate large volumes of semi-structured data without support for natural language interaction or cross-source synthesis. To address this, we introduce ClinAgent, a conversational system based on agentic Retrieval-Augmented Generation (RAG) that enables clinicians and researchers to query clinical trial information in plain language and receive grounded, up-to-date responses across multi-turn interactions. The system centers on a Large Language Model (LLM) agent following the ReAct paradigm, which iteratively reasons over queries, selects among a set of integrated tools, and refines its actions based on intermediate outputs. These tools include a ClinicalTrials.gov search interface, a PubMed module, and a Python-based analyzer operating on a locally cached structured dataset of clinical trials. We evaluate the system using a three-phase framework assessing operational effectiveness, planning quality, tool-use efficiency, and expert qualitative judgments, comparing three LLM backends: Gemini 3.0 Flash and two variants of DeepSeek V3.2 (thinking and non-thinking). Results reveal complementary strengths, with DeepSeek (thinking mode) excelling in planning quality, while Gemini achieves the highest overall performance and strongest expert ratings. Overall, our findings highlight the potential of agentic AI systems to improve the accessibility and synthesis of clinical trial information, supporting more efficient and user-centered biomedical research workflows.

cs.AI↗

arXiv2025

Benchmarking Adversarial Robustness to Bias Elicitation in Large Language Models: Scalable Automated Assessment with LLM-as-a-Judge

The growing integration of Large Language Models (LLMs) into critical societal domains has raised concerns about embedded biases that can perpetuate stereotypes and undermine fairness. Such biases may stem from historical inequalities in training data, linguistic imbalances, or adversarial manipulation. Despite mitigation efforts, recent studies show that LLMs remain vulnerable to adversarial attacks that elicit biased outputs. This work proposes a scalable benchmarking framework to assess LLM robustness to adversarial bias elicitation. Our methodology involves: (i) systematically probing models across multiple tasks targeting diverse sociocultural biases, (ii) quantifying robustness through safety scores using an LLM-as-a-Judge approach, and (iii) employing jailbreak techniques to reveal safety vulnerabilities. To facilitate systematic benchmarking, we release a curated dataset of bias-related prompts, named CLEAR-Bias. Our analysis, identifying DeepSeek V3 as the most reliable judge LLM, reveals that bias resilience is uneven, with age, disability, and intersectional biases among the most prominent. Some small models outperform larger ones in safety, suggesting that training and architecture may matter more than scale. However, no model is fully robust to adversarial elicitation, with jailbreak attacks using low-resource languages or refusal suppression proving effective across model families. We also find that successive LLM generations exhibit slight safety gains, while models fine-tuned for the medical domain tend to be less safe than their general-purpose counterparts.

cs.CL↗

arXiv2025

Is Reasoning All You Need? Probing Bias in the Age of Reasoning Language Models

Reasoning Language Models (RLMs) have gained traction for their ability to perform complex, multi-step reasoning tasks through mechanisms such as Chain-of-Thought (CoT) prompting or fine-tuned reasoning traces. While these capabilities promise improved reliability, their impact on robustness to social biases remains unclear. In this work, we leverage the CLEAR-Bias benchmark, originally designed for Large Language Models (LLMs), to investigate the adversarial robustness of RLMs to bias elicitation. We systematically evaluate state-of-the-art RLMs across diverse sociocultural dimensions, using an LLM-as-a-judge approach for automated safety scoring and leveraging jailbreak techniques to assess the strength of built-in safety mechanisms. Our evaluation addresses three key questions: (i) how the introduction of reasoning capabilities affects model fairness and robustness; (ii) whether models fine-tuned for reasoning exhibit greater safety than those relying on CoT prompting at inference time; and (iii) how the success rate of jailbreak attacks targeting bias elicitation varies with the reasoning mechanisms employed. Our findings reveal a nuanced relationship between reasoning capabilities and bias safety. Surprisingly, models with explicit reasoning, whether via CoT prompting or fine-tuned reasoning traces, are generally more vulnerable to bias elicitation than base models without such mechanisms, suggesting reasoning may unintentionally open new pathways for stereotype reinforcement. Reasoning-enabled models appear somewhat safer than those relying on CoT prompting, which are particularly prone to contextual reframing attacks through storytelling prompts, fictional personas, or reward-shaped instructions. These results challenge the assumption that reasoning inherently improves robustness and underscore the need for more bias-aware approaches to reasoning design.

cs.CL↗

arXiv2025

Dynamic hashtag recommendation in social media with trend shift detection and adaptation

Hashtag recommendation systems have emerged as a key tool for automatically suggesting relevant hashtags and enhancing content categorization and search. However, existing static models struggle to adapt to the highly dynamic nature of social media conversations, where new hashtags constantly emerge and existing ones undergo semantic shifts. To address these challenges, this paper introduces H-ADAPTS (Hashtag recommendAtion by Detecting and adAPting to Trend Shifts), a dynamic hashtag recommendation methodology that employs a trend-aware mechanism to detect shifts in hashtag usage-reflecting evolving trends and topics within social media conversations-and triggers efficient model adaptation based on a (small) set of recent posts. Additionally, the Apache Storm framework is leveraged to support scalable and fault-tolerant analysis of high-velocity social data, enabling the timely detection of trend shifts. Experimental results from two real-world case studies, including the COVID-19 pandemic and the 2020 US presidential election, demonstrate the effectiveness of H-ADAPTS in providing timely and relevant hashtag recommendations by adapting to emerging trends, significantly outperforming existing solutions.

cs.SI↗

arXiv2025

Detecting mental disorder on social media: a ChatGPT-augmented explainable approach

In the digital era, the prevalence of depressive symptoms expressed on social media has raised serious concerns, necessitating advanced methodologies for timely detection. This paper addresses the challenge of interpretable depression detection by proposing a novel methodology that effectively combines Large Language Models (LLMs) with eXplainable Artificial Intelligence (XAI) and conversational agents like ChatGPT. In our methodology, explanations are achieved by integrating BERTweet, a Twitter-specific variant of BERT, into a novel self-explanatory model, namely BERT-XDD, capable of providing both classification and explanations via masked attention. The interpretability is further enhanced using ChatGPT to transform technical explanations into human-readable commentaries. By introducing an effective and modular approach for interpretable depression detection, our methodology can contribute to the development of socially responsible digital platforms, fostering early intervention and support for mental health challenges under the guidance of qualified healthcare professionals.

cs.CL↗

arXiv2025

Are Large Language Models Really Bias-Free? Jailbreak Prompts for Assessing Adversarial Robustness to Bias Elicitation

Large Language Models (LLMs) have revolutionized artificial intelligence, demonstrating remarkable computational power and linguistic capabilities. However, these models are inherently prone to various biases stemming from their training data. These include selection, linguistic, and confirmation biases, along with common stereotypes related to gender, ethnicity, sexual orientation, religion, socioeconomic status, disability, and age. This study explores the presence of these biases within the responses given by the most recent LLMs, analyzing the impact on their fairness and reliability. We also investigate how known prompt engineering techniques can be exploited to effectively reveal hidden biases of LLMs, testing their adversarial robustness against jailbreak prompts specially crafted for bias elicitation. Extensive experiments are conducted using the most widespread LLMs at different scales, confirming that LLMs can still be manipulated to produce biased or inappropriate responses, despite their advanced capabilities and sophisticated alignment processes. Our findings underscore the importance of enhancing mitigation techniques to address these safety issues, toward a more sustainable and inclusive artificial intelligence.

cs.CL↗

arXiv2024

Block size estimation for data partitioning in HPC applications using machine learning techniques

The extensive use of HPC infrastructures and frameworks for running dataintensive applications has led to a growing interest in data partitioning techniques and strategies. In fact, application performance can be heavily affected by how data are partitioned, which in turn depends on the selected size for data blocks, i.e. the block size. Therefore, finding an effective partitioning, i.e. a suitable block size, is a key strategy to speed-up parallel data-intensive applications and increase scalability. This paper describes a methodology, namely BLEST-ML (BLock size ESTimation through Machine Learning), for block size estimation that relies on supervised machine learning techniques. The proposed methodology was evaluated by designing an implementation tailored to dislib, a distributed computing library highly focused on machine learning algorithms built on top of the PyCOMPSs framework. We assessed the effectiveness of the provided implementation through an extensive experimental evaluation considering different algorithms from dislib, datasets, and infrastructures, including the MareNostrum 4 supercomputer. The results we obtained show the ability of BLEST-ML to efficiently determine a suitable way to split a given dataset, thus providing a proof of its applicability to enable the efficient execution of data-parallel applications in high performance environments.

cs.DC↗