Cristian Muñoz

Mengfei Liang, Archish Arun, Zekun Wu et al.

Hallucination, the generation of factually incorrect content, is a growing challenge in Large Language Models (LLMs). Existing detection and mitigation methods are often isolated and insufficient for domain-specific needs, lacking a standardized pipeline. This paper introduces THaMES (Tool for Hallucination Mitigations and EvaluationS), an integrated framework and library addressing this gap. THaMES offers an end-to-end solution for evaluating and mitigating hallucinations in LLMs, featuring automated test set generation, multifaceted benchmarking, and adaptable mitigation strategies. It automates test set creation from any corpus, ensuring high data quality, diversity, and cost-efficiency through techniques like batch processing, weighted sampling, and counterfactual validation. THaMES assesses a model's ability to detect and reduce hallucinations across various tasks, including text generation and binary classification, applying optimal mitigation strategies like In-Context Learning (ICL), Retrieval Augmented Generation (RAG), and Parameter-Efficient Fine-tuning (PEFT). Evaluations of state-of-the-art LLMs using a knowledge base of academic papers, political news, and Wikipedia reveal that commercial models like GPT-4o benefit more from RAG than ICL, while open-weight models like Llama-3.1-8B-Instruct and Mistral-Nemo gain more from ICL. Additionally, PEFT significantly enhances the performance of Llama-3.1-8B-Instruct in both evaluation tasks.

Cristian Muñoz, Sara Zannone, Umar Mohammed et al.

Recent advancements in GANs and diffusion models have enabled the creation of high-resolution, hyper-realistic images. However, these models may misrepresent certain social groups and present bias. Understanding bias in these models remains an important research question, especially for tasks that support critical decision-making and could affect minorities. The contribution of this work is a novel analysis covering architectures and embedding spaces for fine-grained understanding of bias over three approaches: generators, attribute modifier, and post-processing bias mitigators. This work shows that generators suffer from bias across all social groups with attribute preferences such as between 75%-85% for whiteness and 60%-80% for the female gender (for all trained CelebA models) and low probabilities of generating children and older men. Modifier and mitigators work as post-processor and change the generator performance. For instance, attribute channel perturbation strategies modify the embedding spaces. We quantify the influence of this change on group fairness by measuring the impact on image quality and group features. Specifically, we use the Fréchet Inception Distance (FID), the Face Matching Error and the Self-Similarity score. For Interfacegan, we analyze one and two attribute channel perturbations and examine the effect on the fairness distribution and the quality of the image. Finally, we analyzed the post-processing bias mitigators, which are the fastest and most computationally efficient way to mitigate bias. We find that these mitigation techniques show similar results on KL divergence and FID score, however, self-similarity scores show a different feature concentration on the new groups of the data distribution. The weaknesses and ongoing challenges described in this work must be considered in the pursuit of creating fair and unbiased face generation models.

Navya Jain, Zekun Wu, Cristian Munoz et al.

The manipulation of the personality traits of large language models (LLMs) has emerged as a key area of research. Methods like prompt-based In-Context Knowledge Editing (IKE) and gradient-based Model Editor Networks (MEND) have been explored but show irregularity and variability; IKE depends on the prompt, leading to variability and sensitivity, while MEND yields inconsistent and gibberish outputs. To address this, we employed Opinion QA Based Parameter-Efficient Fine-Tuning (PEFT), specifically Quantized Low-Rank Adaptation (QLoRA), to manipulate the Big Five personality traits: Openness, Conscientiousness, Extraversion, Agreeableness, and Neuroticism. After PEFT, models such as Mistral-7B-Instruct and LLaMA-2-7B-chat showed a latent behaviour by generating emojis for certain traits, despite no emojis being present in the PEFT data. For instance, LLaMA-2-7B-chat generated emojis in 99.5\% of extraversion-related test instances, while Mistral-7B-Instruct did so in 92.5\% of openness-related test instances. ICL Explainability analysis indicated that the LLMs used emojis intentionally to express these traits. Mechanistic Interpretability analysis showed that this latent behaviour of LLMs could be traced to specific neurons that became activated or amplified after PEFT. This paper provides a number of novel contributions. First, introducing an Opinion QA dataset for PEFT-driven personality manipulation; second, developing metric models to benchmark LLM personality traits; third, demonstrating PEFT's superiority over IKE in personality manipulation; and finally, analysing and validating emoji usage through explainability methods such as Mechanistic Interpretability and In-context learning Explainability methods.

Cristian Munoz, Kleyton da Costa, Bernardo Modenesi et al.

The rapid integration of artificial intelligence (AI) into various industries has introduced new challenges in governance and regulation, particularly regarding the understanding of complex AI systems. A critical demand from decision-makers is the ability to explain the results of machine learning models, which is essential for fostering trust and ensuring ethical AI practices. In this paper, we develop six distinct model-agnostic metrics designed to quantify the extent to which model predictions can be explained. These metrics measure different aspects of model explainability, ranging from local importance, global importance, and surrogate predictions, allowing for a comprehensive evaluation of how models generate their outputs. Furthermore, by computing our metrics, we can rank models in terms of explainability criteria such as importance concentration and consistency, prediction fluctuation, and surrogate fidelity and stability, offering a valuable tool for selecting models based not only on accuracy but also on transparency. We demonstrate the practical utility of these metrics on classification and regression tasks, and integrate these metrics into an existing Python package for public use.

Felipe A. Quezada, Carlos F. Navarro, Cristian Muñoz et al.

Vision Transformers (ViTs) have successfully been applied to image classification problems where large annotated datasets are available. On the other hand, when fewer annotations are available, such as in biomedical applications, image augmentation techniques like introducing image variations or combinations have been proposed. However, regarding ViT patch sampling, less has been explored outside grid-based strategies. In this work, we propose Random Vision Transformer Tokens (RaViTT), a random patch sampling strategy that can be incorporated into existing ViTs. We experimentally evaluated RaViTT for image classification, comparing it with a baseline ViT and state-of-the-art (SOTA) augmentation techniques in 4 datasets, including ImageNet-1k and CIFAR-100. Results show that RaViTT increases the accuracy of the baseline in all datasets and outperforms the SOTA augmentation techniques in 3 out of 4 datasets by a significant margin +1.23% to +4.32%. Interestingly, RaViTT accuracy improvements can be achieved even with fewer tokens, thus reducing the computational load of any ViT model for a given accuracy value.

Zekun Wu, Seonglae Cho, Umar Mohammed et al.

Open-source AI libraries are foundational to modern AI systems, yet they present significant, underexamined risks spanning security, licensing, maintenance, supply chain integrity, and regulatory compliance. We introduce LibVulnWatch, a system that leverages recent advances in large language models and agentic workflows to perform deep, evidence-based evaluations of these libraries. Built on a graph-based orchestration of specialized agents, the framework extracts, verifies, and quantifies risk using information from repositories, documentation, and vulnerability databases. LibVulnWatch produces reproducible, governance-aligned scores across five critical domains, publishing results to a public leaderboard for ongoing ecosystem monitoring. Applied to 20 widely used libraries, including ML frameworks, LLM inference engines, and agent orchestration tools, our approach covers up to 88% of OpenSSF Scorecard checks while surfacing up to 19 additional risks per library, such as critical RCE vulnerabilities, missing SBOMs, and regulatory gaps. By integrating advanced language technologies with the practical demands of software risk assessment, this work demonstrates a scalable, transparent mechanism for continuous supply chain evaluation and informed library selection.

Airlie Hilliard, Cristian Munoz, Zekun Wu et al.

Large Language Models (LLMs) are increasingly being utilized by both candidates and employers in the recruitment context. However, with this comes numerous ethical concerns, particularly related to the lack of transparency in these "black-box" models. Although previous studies have sought to increase the transparency of these models by investigating the personality traits of LLMs, many of the previous studies have provided them with personality assessments to complete. On the other hand, this study seeks to obtain a better understanding of such models by examining their output variations based on different input prompts. Specifically, we use a novel elicitation approach using prompts derived from common interview questions, as well as prompts designed to elicit particular Big Five personality traits to examine whether the models were susceptible to trait-activation like humans are, to measure their personality based on the language used in their outputs. To do so, we repeatedly prompted multiple LMs with different parameter sizes, including Llama-2, Falcon, Mistral, Bloom, GPT, OPT, and XLNet (base and fine tuned versions) and examined their personality using classifiers trained on the myPersonality dataset. Our results reveal that, generally, all LLMs demonstrate high openness and low extraversion. However, whereas LMs with fewer parameters exhibit similar behaviour in personality traits, newer and LMs with more parameters exhibit a broader range of personality traits, with increased agreeableness, emotional stability, and openness. Furthermore, a greater number of parameters is positively associated with openness and conscientiousness. Moreover, fine-tuned models exhibit minor modulations in their personality traits, contingent on the dataset. Implications and directions for future research are discussed.

Jose David Bermudez Castro, Ricardo Rei, Jose E. Ruiz et al.

The coronavirus outbreak became a major concern for society worldwide. Technological innovation and ingenuity are essential to fight COVID-19 pandemic and bring us one step closer to overcome it. Researchers over the world are working actively to find available alternatives in different fields, such as the Healthcare System, pharmaceutic, health prevention, among others. With the rise of artificial intelligence (AI) in the last 10 years, IA-based applications have become the prevalent solution in different areas because of its higher capability, being now adopted to help combat against COVID-19. This work provides a fast detection system of COVID-19 characteristics in X-Ray images based on deep learning (DL) techniques. This system is available as a free web deployed service for fast patient classification, alleviating the high demand for standards method for COVID-19 diagnosis. It is constituted of two deep learning models, one to differentiate between X-Ray and non-X-Ray images based on Mobile-Net architecture, and another one to identify chest X-Ray images with characteristics of COVID-19 based on the DenseNet architecture. For real-time inference, it is provided a pair of dedicated GPUs, which reduce the computational time. The whole system can filter out non-chest X-Ray images, and detect whether the X-Ray presents characteristics of COVID-19, highlighting the most sensitive regions.