Alessio Buscemi

Tom Lucas, Alessio Buscemi, Alfredo Capozucca et al.

Assessing whether Large Language Models outputs are factually grounded, epistemically calibrated, and methodologically reproducible is a prerequisite for responsible AI deployment. Yet auditing LLMs remains inaccessible to non-technical practitioners: existing tools require programming expertise and non-trivial environment setup, and cloud-hosted platforms transmit evaluation data to external services, creating barriers for domain experts and compliance officers legally responsible for AI oversight. We introduce LLM-FACETS (LLM FActuality Cross-EvaluaTion System): an open-source framework with a browser-accessible interface and a plugin architecture, structured around three practitioner profiles (technical experts, domain experts, compliance officers) that mirror the stakeholder categories identified in the EU AI Act and the NIST AI Risk Management Framework. The architecture makes data flows explicit: deterministic metrics (BLEU, ROUGE, BERTScore) run entirely within the self-hosted server with no outbound transmission; LLM-judge metrics contact external APIs explicitly, with users retaining full credential control. The framework operationalizes transparency through three mechanisms: token-level log-probability visualization for epistemic uncertainty, multi-judge consensus to mitigate judge bias, and RAG Triad metrics (Faithfulness, Answer Relevance, Context Relevance) to detect and localize hallucinations. A plugin architecture allows any new metric or dataset to be integrated without modifying the evaluation pipeline. The open-source implementation enables cross-checking across multiple metrics targeting the same property, ensuring reproducibility and decoupling AI accountability from the teams building the systems assessed. We verify the framework through cross-validation of 18 metric implementations against canonical reference libraries.

Trung-Kiet Huynh, Dao-Sy Duy-Minh, Thanh-Bang Cao et al.

As LLMs increasingly act as autonomous agents in interactive and multi-agent settings, understanding their strategic behavior is critical for safety, coordination, and AI-driven social and economic systems. We investigate how payoff magnitude and linguistic context shape LLM strategies in repeated social dilemmas, using a payoff-scaled Prisoner's Dilemma to isolate sensitivity to incentive strength. Across models and languages, we observe consistent behavioral patterns, including incentive-sensitive conditional strategies and cross-linguistic divergence. To interpret these dynamics, we train supervised classifiers on canonical repeated-game strategies and apply them to LLM decisions, revealing systematic, model- and language-dependent behavioral intentions, with linguistic framing sometimes matching or exceeding architectural effects. Our results provide a unified framework for auditing LLMs as strategic agents and highlight cooperation biases with direct implications for AI governance and multi-agent system design.

Trung-Kiet Huynh, Duy-Minh Dao-Sy, Thanh-Bang Cao et al.

As Large Language Models (LLMs) increasingly operate as autonomous decision-makers in interactive and multi-agent systems and human societies, understanding their strategic behaviour has profound implications for safety, coordination, and the design of AI-driven social and economic infrastructures. Assessing such behaviour requires methods that capture not only what LLMs output, but the underlying intentions that guide their decisions. In this work, we extend the FAIRGAME framework to systematically evaluate LLM behaviour in repeated social dilemmas through two complementary advances: a payoff-scaled Prisoners Dilemma isolating sensitivity to incentive magnitude, and an integrated multi-agent Public Goods Game with dynamic payoffs and multi-agent histories. These environments reveal consistent behavioural signatures across models and languages, including incentive-sensitive cooperation, cross-linguistic divergence and end-game alignment toward defection. To interpret these patterns, we train traditional supervised classification models on canonical repeated-game strategies and apply them to FAIRGAME trajectories, showing that LLMs exhibit systematic, model- and language-dependent behavioural intentions, with linguistic framing at times exerting effects as strong as architectural differences. Together, these findings provide a unified methodological foundation for auditing LLMs as strategic agents and reveal systematic cooperation biases with direct implications for AI governance, collective decision-making, and the design of safe multi-agent systems.

Alessio Buscemi, Daniele Proverbio, Alessandro Di Stefano et al.

LLMs-based agents increasingly operate in multi-agent environments where strategic interaction and coordination are required. While existing work has largely focused on individual agents or on interacting agents sharing explicit communication, less is known about how interacting agents coordinate implicitly. In particular, agents may engage in covert communication, relying on indirect or non-linguistic signals embedded in their actions rather than on explicit messages. This paper presents a game-theoretic study of covert communication in LLM-driven multi-agent systems. We analyse interactions across four canonical game-theoretic settings under different communication regimes, including explicit, restricted, and absent communication. Considering heterogeneous agent personalities and both one-shot and repeated games, we characterise when covert signals emerge and how they shape coordination and strategic outcomes.

Alessio Buscemi

Large Language Models (LLMs) are advanced Artificial Intelligence (AI) systems that have undergone extensive training using large datasets in order to understand and produce language that closely resembles that of humans. These models have reached a level of proficiency where they are capable of successfully completing university exams across several disciplines and generating functional code to handle novel problems. This research investigates the coding proficiency of ChatGPT 3.5, a LLM released by OpenAI in November 2022, which has gained significant recognition for its impressive text generating and code creation capabilities. The skill of the model in creating code snippets is evaluated across 10 various programming languages and 4 different software domains. Based on the findings derived from this research, major unexpected behaviors and limitations of the model have been identified. This study aims to identify potential areas for development and examine the ramifications of automated code generation on the evolution of programming languages and on the tech industry.

Alessio Buscemi, Thibault Simonetto, Daniele Pagani et al.

The systematic assessment of AI systems is increasingly vital as these technologies enter high-stakes domains. To address this, the EU's Artificial Intelligence Act introduces AI Regulatory Sandboxes (AIRS): supervised environments where AI systems can be tested under the oversight of Competent Authorities (CAs), balancing innovation with compliance, particularly for startups and SMEs. Yet significant challenges remain: assessment methods are fragmented, tests lack standardisation, and feedback loops between developers and regulators are weak. To bridge these gaps, we propose the Sandbox Configurator, a modular open-source framework that enables users to select domain-relevant tests from a shared library and generate customised sandbox environments with integrated dashboards. Its plug-in architecture aims to support both open and proprietary modules, fostering a shared ecosystem of interoperable AI assessment services. The framework aims to address multiple stakeholders: CAs gain structured workflows for applying legal obligations; technical experts can integrate robust evaluation methods; and AI providers access a transparent pathway to compliance. By promoting cross-border collaboration and standardisation, the Sandbox Configurator's goal is to support a scalable and innovation-friendly European infrastructure for trustworthy AI governance.

Arina Caraus, Alessio Buscemi, Sumit Kumar et al.

Large Language Models (LLMs) have shown remarkable capabilities across various fields. However, their performance in technical domains such as telecommunications remains underexplored. This paper evaluates two open-source LLMs, Gemma 3 27B and DeepSeek R1 32B, on factual and reasoning-based questions derived from advanced wireless communications material. We construct a benchmark of 105 question-answer pairs and assess performance using lexical metrics, semantic similarity, and LLM-as-a-judge scoring. We also analyze consistency, judgment reliability, and hallucination through source attribution and score variance. Results show that Gemma excels in semantic fidelity and LLM-rated correctness, while DeepSeek demonstrates slightly higher lexical consistency. Additional findings highlight current limitations in telecom applications and the need for domain-adapted models to support trustworthy Artificial Intelligence (AI) assistants in engineering.

Nataliya Balabanova, Adeela Bashir, Paolo Bova et al.

This paper investigates the complex interplay between AI developers, regulators, users, and the media in fostering trustworthy AI systems. Using evolutionary game theory and large language models (LLMs), we model the strategic interactions among these actors under different regulatory regimes. The research explores two key mechanisms for achieving responsible governance, safe AI development and adoption of safe AI: incentivising effective regulation through media reporting, and conditioning user trust on commentariats' recommendation. The findings highlight the crucial role of the media in providing information to users, potentially acting as a form of "soft" regulation by investigating developers or regulators, as a substitute to institutional AI regulation (which is still absent in many regions). Both game-theoretic analysis and LLM-based simulations reveal conditions under which effective regulation and trustworthy AI development emerge, emphasising the importance of considering the influence of different regulatory regimes from an evolutionary game-theoretic perspective. The study concludes that effective governance requires managing incentives and costs for high quality commentaries.

Alessio Buscemi, Daniele Proverbio, Alessandro Di Stefano et al.

Letting AI agents interact in multi-agent applications adds a layer of complexity to the interpretability and prediction of AI outcomes, with profound implications for their trustworthy adoption in research and society. Game theory offers powerful models to capture and interpret strategic interaction among agents, but requires the support of reproducible, standardized and user-friendly IT frameworks to enable comparison and interpretation of results. To this end, we present FAIRGAME, a Framework for AI Agents Bias Recognition using Game Theory. We describe its implementation and usage, and we employ it to uncover biased outcomes in popular games among AI agents, depending on the employed Large Language Model (LLM) and used language, as well as on the personality trait or strategic knowledge of the agents. Overall, FAIRGAME allows users to reliably and easily simulate their desired games and scenarios and compare the results across simulation campaigns and with game-theoretic predictions, enabling the systematic discovery of biases, the anticipation of emerging behavior out of strategic interplays, and empowering further research into strategic decision-making using LLM agents.

Alessio Buscemi, Daniele Proverbio, Paolo Bova et al.

There is general agreement that fostering trust and cooperation within the AI development ecosystem is essential to promote the adoption of trustworthy AI systems. By embedding Large Language Model (LLM) agents within an evolutionary game-theoretic framework, this paper investigates the complex interplay between AI developers, regulators and users, modelling their strategic choices under different regulatory scenarios. Evolutionary game theory (EGT) is used to quantitatively model the dilemmas faced by each actor, and LLMs provide additional degrees of complexity and nuances and enable repeated games and incorporation of personality traits. Our research identifies emerging behaviours of strategic AI agents, which tend to adopt more "pessimistic" (not trusting and defective) stances than pure game-theoretic agents. We observe that, in case of full trust by users, incentives are effective to promote effective regulation; however, conditional trust may deteriorate the "social pact". Establishing a virtuous feedback between users' trust and regulators' reputation thus appears to be key to nudge developers towards creating safe AI. However, the level at which this trust emerges may depend on the specific LLM used for testing. Our results thus provide guidance for AI regulation systems, and help predict the outcome of strategic LLM agents, should they be used to aid regulation itself.

Alessio Buscemi, Daniele Proverbio

Democratic opinion-forming may be manipulated if newspapers' alignment to political or economical orientation is ambiguous. Various methods have been developed to better understand newspapers' positioning. Recently, the advent of Large Language Models (LLM), and particularly the pre-trained LLM chatbots like ChatGPT or Gemini, hold disruptive potential to assist researchers and citizens alike. However, little is know on whether LLM assessment is trustworthy: do single LLM agrees with experts' assessment, and do different LLMs answer consistently with one another? In this paper, we address specifically the second challenge. We compare how four widely employed LLMs rate the positioning of newspapers, and compare if their answers align with one another. We observe that this is not the case. Over a woldwide dataset, articles in newspapers are positioned strikingly differently by single LLMs, hinting to inconsistent training or excessive randomness in the algorithms. We thus raise a warning when deciding which tools to use, and we call for better training and algorithm development, to cover such significant gap in a highly sensitive matter for democracy and societies worldwide. We also call for community engagement in benchmark evaluation, through our open initiative navai.pro.

Alessio Buscemi, Cédric Lothritz, Sergio Morales et al.

Large Language Models (LLMs) have exhibited impressive natural language processing capabilities but often perpetuate social biases inherent in their training data. To address this, we introduce MultiLingual Augmented Bias Testing (MLA-BiTe), a framework that improves prior bias evaluation methods by enabling systematic multilingual bias testing. MLA-BiTe leverages automated translation and paraphrasing techniques to support comprehensive assessments across diverse linguistic settings. In this study, we evaluate the effectiveness of MLA-BiTe by testing four state-of-the-art LLMs in six languages -- including two low-resource languages -- focusing on seven sensitive categories of discrimination.

Alessio Buscemi, Tom Deckenbrunnen, Fahria Kabir et al.

The implementation of the AI Act requires practical mechanisms to verify compliance with legal obligations, yet concrete and operational mappings from high-level requirements to verifiable assessment activities remain limited, contributing to uneven readiness across Member States. This paper presents a structured mapping that translates high-level AI Act requirements into concrete, implementable verification activities applicable across the AI lifecycle. The mapping is derived through a systematic process in which legal requirements are decomposed into operational sub-requirements and grounded in authoritative standards and recognised practices. From this basis, verification activities are identified and characterised along two dimensions: the type of verification performed and the lifecycle target to which it applies. By making explicit the link between regulatory intent and technical and organisational assurance practices, the proposed mapping reduces interpretive uncertainty and provides a reusable reference for consistent, technology-agnostic compliance verification under the AI Act.

Henrique Correia da Fonseca, António Fernandes, Zhao Song et al.

When developers of artificial intelligence (AI) products need to decide between profit and safety for the users, they likely choose profit. Untrustworthy AI technology must come packaged with tangible negative consequences. Here, we envisage those consequences as the loss of reputation caused by media coverage of their misdeeds, disseminated to the public. We explore whether media coverage has the potential to push AI creators into the production of safe products, enabling widespread adoption of AI technology. We created artificial populations of self-interested creators and users and studied them through the lens of evolutionary game theory. Our results reveal that media is indeed able to foster cooperation between creators and users, but not always. Cooperation does not evolve if the quality of the information provided by the media is not reliable enough, or if the costs of either accessing media or ensuring safety are too high. By shaping public perception and holding developers accountable, media emerges as a powerful soft regulator -- guiding AI safety even in the absence of formal government oversight.

Daniele Proverbio, Alessio Buscemi, Alessandro Di Stefano et al.

Game theory has long served as a foundational tool in cybersecurity to test, predict, and design strategic interactions between attackers and defenders. The recent advent of Large Language Models (LLMs) offers new tools and challenges for the security of computer systems; In this work, we investigate whether classical game-theoretic frameworks can effectively capture the behaviours of LLM-driven actors and bots. Using a reproducible framework for game-theoretic LLM agents, we investigate two canonical scenarios -- the one-shot zero-sum game and the dynamic Prisoner's Dilemma -- and we test whether LLMs converge to expected outcomes or exhibit deviations due to embedded biases. Our experiments involve four state-of-the-art LLMs and span five natural languages, English, French, Arabic, Vietnamese, and Mandarin Chinese, to assess linguistic sensitivity. For both games, we observe that the final payoffs are influenced by agents characteristics such as personality traits or knowledge of repeated rounds. Moreover, we uncover an unexpected sensitivity of the final payoffs to the choice of languages, which should warn against indiscriminate application of LLMs in cybersecurity applications and call for in-depth studies, as LLMs may behave differently when deployed in different countries. We also employ quantitative metrics to evaluate the internal consistency and cross-language stability of LLM agents, to help guide the selection of the most stable LLMs and optimising models for secure applications.

Alessio Buscemi, Daniele Proverbio

The ethical implications and potentials for misuse of Generative Artificial Intelligence are increasingly worrying topics. This paper explores how easily the default ethical guardrails of ChatGPT, using its latest customization features, can be bypassed by simple prompts and fine-tuning, that can be effortlessly accessed by the broad public. This malevolently altered version of ChatGPT, nicknamed "RogueGPT", responded with worrying behaviours, beyond those triggered by jailbreak prompts. We conduct an empirical study of RogueGPT responses, assessing its flexibility in answering questions pertaining to what should be disallowed usage. Our findings raise significant concerns about the model's knowledge about topics like illegal drug production, torture methods and terrorism. The ease of driving ChatGPT astray, coupled with its global accessibility, highlights severe issues regarding the data quality used for training the foundational model and the implementation of ethical safeguards. We thus underline the responsibilities and dangers of user-driven modifications, and the broader effects that these may have on the design of safeguarding and ethical modules implemented by AI programmers.

Alessio Buscemi, Daniele Proverbio

Automated sentiment analysis using Large Language Model (LLM)-based models like ChatGPT, Gemini or LLaMA2 is becoming widespread, both in academic research and in industrial applications. However, assessment and validation of their performance in case of ambiguous or ironic text is still poor. In this study, we constructed nuanced and ambiguous scenarios, we translated them in 10 languages, and we predicted their associated sentiment using popular LLMs. The results are validated against post-hoc human responses. Ambiguous scenarios are often well-coped by ChatGPT and Gemini, but we recognise significant biases and inconsistent performance across models and evaluated human languages. This work provides a standardised methodology for automated sentiment analysis evaluation and makes a call for action to further improve the algorithms and their underlying data, to improve their performance, interpretability and applicability.