Searcharxiv⌕ Search

arXiv subjects

Nouar AlDahoul

Publications and source records attributed to Nouar AlDahoul.

At least 19 recordsLinked to original sources

From Leniency to Suspicion: How an Open Post-Training Recipe Changes Whom LLM Fact-Checkers Believe

LLMs increasingly fact-check online content with the poster's identity in view. However, it remains unclear which post-training changes how much a model's truth judgement depends on the poster's social class, and how such a change happens inside the model. This paper investigates job-based doubt, i.e., judging a claim false more often when the poster has a lower-status job, using fact-checked claims with randomised poster profiles in base and post-trained checkpoints of six model families. Our results reveal that: 1) post-training creates such doubt only with the open Tülu-3 recipe (OLMo-2 32B, Tülu-3 70B), not with Meta's, Alibaba's or Mistral's; the effect is under one percentage point but statistically reliable, exceeding training drift and replicating on independent claim sets; 2) in OLMo-2 32B, the model does not start noticing the poster's job more, but starts interpreting it differently: a lower-status job pushes the base model toward "true" and the post-trained model toward "false"; and 3) this flip is carried by a single residual-stream direction and happens at supervised fine-tuning. The mechanism was confirmed on 400 new claims with pre-specified predictions. None of seven deployed commercial models doubts lower-status posters more. Our work underscores the need to audit speaker bias per training recipe.

cs.AI↗

Need or Reputation? Region, National Income, and Academic Status in LLM Gatekeeping Decisions

Equitable access to scientific knowledge often depends on informal gatekeeping decisions, particularly when resources such as paywalled articles, nonpublic datasets, or a researcher's CV must be shared selectively. We introduce a controlled simulation framework in which LLM-based professors must grant access to only one requester. Across prompts, requesters vary systematically by global region (Global North vs. Global South) and academic seniority, while all other factors remain constant. Most models prioritize PhD candidates, although preferences vary by model and scenario (e.g., Claude favors tenured professors when the request is for the professor's CV), and the smaller models' status choices are sensitive to the order in which options are presented. When the requesters' regions differ, the models split into two groups. The three large proprietary LLMs systematically favor requesters from the Global South, a pro-equity bias consistent with their safety alignment, whereas the two small open-weight models reverse this preference and favor the Global North, possibly reflecting weaker alignment or the geographic skew of their pre-training data. Linking choices to national income reveals that the large models' preference largely tracks economic need rather than the regional label: they strongly favor requesters from low-income countries, but their preference for the Global South is weak or absent when both countries have equal income, whereas the small models favor the Global North regardless of income. Because model scale, alignment, and training data are confounded in our sample, these explanations remain hypotheses for future work. Our findings show that LLMs embed differing normative assumptions about need and reputation that can shape gatekeeping decisions, which highlights the need to audit AI systems for fairness and value alignment before such tasks are delegated to them.

cs.CY↗

Veracity labels flip the emotional tone of language models but leave racial disparities intact

Large language models (LLMs) increasingly deliver information through personas, but it is unclear whether correcting the facts also makes their framing consistent across identity labels. We audited four LLMs (GPT-5.4 mini, NVIDIA Nemotron 3 Nano, Llama 4 Scout, and Claude Haiku 4.5), which rated simulated affect on six dimensions (mood, anger, fear, confidence, perceived control, and mental state) in response to fact-checked false and true headlines presented without and with a veracity label. Experiment 1 evaluated 1,000 false and 1,000 true headlines without personas; Experiment 2 evaluated 300 of each under 12 personas crossing race, gender, and age. The label strongly changed the emotional tone: ordinal logistic regressions with headline-cluster bootstrap inference showed that refuting false headlines shifted ratings from mostly negative to mostly positive for GPT, Llama, and Claude (e.g., Claude's "confident" ratings rose from 22% to 99.6%), whereas Nemotron showed smaller, mixed shifts, and confirming true headlines produced only small shifts. The label did not, however, remove persona-associated disparities. The models assigned more negative simulated affect to Black than to White personas in 82 of 84 statistically significant comparisons across models and conditions, both without and with the label, and the disparity persisted on headlines unrelated to race; Asian and female personas were also predominantly assigned more negative affect, whereas age effects varied by model and condition. Factual correction and demographic consistency are therefore distinct properties of LLM behavior, and persona-conditioned systems should be audited for both before deployment in sensitive contexts.

cs.CY↗

NYUAD at ImageEval Shared Tasks: A Multimodal LLM for Audio-Visual Question Answering and Hallucination Detection in English and Modern Standard Arabic

The increasing adoption of multimodal large language models (MLLMs) has enabled more natural interaction with visual and spoken information, creating new opportunities for intelligent audio-visual question answering (AVQA) and hallucination detection systems. AVQA extends traditional visual question answering by requiring models to jointly understand an input image and a spoken question to generate accurate, context-aware responses. Despite recent advances, AVQA and hallucination detection tasks remain challenging for modern standard Arabic (MSA) due to the limited availability of multimodal datasets and the need to reason across Arabic speech and text modalities alongside visual inputs. In this paper, we present an MLLM-based framework for AVQA that takes an image and a spoken question as input and generates answers. In addition, we utilized this framework to detect hallucination in text-image pairs. The proposed approach is evaluated on the ImageEval 2026 Task (Ayn-VQA) benchmark, which focuses on culturally grounded Arabic AVQA. Experimental results demonstrate that the proposed framework effectively understands spoken queries, grounds their responses in the visual content, and produces accurate answers. The results underscore the capacity and limitations of different LLM architectures for both English and MSA and under various conditions.

cs.CL↗

NYUAD at ArGuard Shared Tasks: Multimodal Embedding Models for Detecting Arabic Hateful Memes and Unsafe Prompts

The rapid growth of social media and generative AI has significantly increased the volume of Arabic textual content, memes, and user prompts shared across online platforms. While these media facilitate communication, creativity, and information exchange, they can also be exploited to disseminate hate speech, harmful content, and unsafe instructions. As a result, there is an increasing need for reliable automated methods to identify hateful Arabic memes and harmful (unsafe) prompts. This paper leverages pre-trained and fine-tuned multilingual embedding models to learn rich semantic representations from textual and visual content. The evaluation is conducted using a dataset of Arabic memes and prompts proposed in the ArabicNLP ArGuard 2026 challenge. The results underscore the capacity of large language model (LLM)-based embedding models to deliver superior performance. Developing robust detection systems is essential for improving content moderation and fostering a more secure and trustworthy online environment for Arabic-speaking users.

cs.CL↗

Fine-tuned Vision Language Model for Localization of Parasitic Eggs in Microscopic Images

Soil-transmitted helminth (STH) infections continuously affect a large proportion of the global population, particularly in tropical and sub-tropical regions, where access to specialized diagnostic expertise is limited. Although manual microscopic diagnosis of parasitic eggs remains the diagnostic gold standard, the approach can be labour-intensive, time-consuming, and prone to human error. This paper aims to utilize a vision language model (VLM) such as Microsoft Florence that was fine-tuned to localize all parasitic eggs within microscopic images. The preliminary results show that our localization VLM performs comparatively better than the other object detection methods, such as EfficientDet, with an mIOU of 0.94. This finding demonstrates the potential of the proposed VLM to serve as a core component of an automated framework, offering a scalable engineering solution for intelligent parasitological diagnosis.

cs.CV↗

Semantic-Aware Advanced Persistent Threat Detection Using Autoencoders on LLM-Encoded System Logs

Advanced Persistent Threats (APTs) are among the most challenging cyberattacks to detect. They are carried out by highly skilled attackers who carefully study their targets and operate in a stealthy, long-term manner. Because APTs exhibit "low-and-slow" behavior, traditional statistical methods and shallow machine learning techniques often fail to detect them. Previous research on APT detection has explored machine learning approaches and provenance graph analysis. However, provenance-based methods often fail to capture the semantic intent behind system activities. This paper proposes a novel anomaly detection approach that leverages semantic embeddings generated by Large Language Models (LLMs). The method enhances APT detection by extracting meaningful semantic representations from unstructured system log data. First, raw system logs are transformed into high-dimensional semantic embeddings using a pre-trained transformer model. These embeddings are then analyzed using an Autoencoder (AE) to identify anomalous and potentially malicious patterns. The proposed method is evaluated using the DARPA Transparent Computing (TC) dataset, which contains realistic APT attack scenarios generated by red teams in live environments. Experimental results show that the AE trained on LLM-derived embeddings outperforms widely used unsupervised baseline methods, including Isolation Forest (IForest), One-Class Support Vector Machine (OC-SVM), and Principal Component Analysis (PCA). Performance is measured using the Area Under the Receiver Operating Characteristic Curve (AUC-ROC), where the proposed approach consistently achieves superior results, even in complex threat scenarios. These findings highlight the importance of semantic understanding in detecting non-linear and stealthy attack behaviors that are often missed by conventional detection techniques.

cs.CR↗

Real-Time Human Detection for Aerial Captured Video Sequences via Deep Models

Human detection in videos plays an important role in various real-life applications. Most traditional approaches depend on utilizing handcrafted features, which are problem-dependent and optimal for specific tasks. Moreover, they are highly susceptible to dynamical events such as illumination changes, camera jitter, and variations in object sizes. On the other hand, the proposed feature learning approaches are cheaper and easier because highly abstract and discriminative features can be produced automatically without the need of expert knowledge. In this paper, we utilize automatic feature learning methods, which combine optical flow and three different deep models (i.e., supervised convolutional neural network (S-CNN), pretrained CNN feature extractor, and hierarchical extreme learning machine) for human detection in videos captured using a nonstatic camera on an aerial platform with varying altitudes. The models are trained and tested on the publicly available and highly challenging UCF-ARG aerial dataset. The comparison between these models in terms of training, testing accuracy, and learning speed is analyzed. The performance evaluation considers five human actions (digging, waving, throwing, walking, and running). Experimental results demonstrated that the proposed methods are successful for the human detection task. The pretrained CNN produces an average accuracy of 98.09%. S-CNN produces an average accuracy of 95.6% with softmax and 91.7% with Support Vector Machines (SVM). H-ELM has an average accuracy of 95.9%. Using a normal Central Processing Unit (CPU), H-ELM's training time takes 445 seconds. Learning in S-CNN takes 770 seconds with a high-performance Graphical Processing Unit (GPU).

cs.LG↗

Enhancing Password Security Through a High-Accuracy Scoring Framework Using Random Forests

Password security plays a crucial role in cybersecurity, yet traditional password strength meters, which rely on static rules like character-type requirements, often fail. Such methods are easily bypassed by common password patterns (e.g., 'P@ssw0rd1!'), giving users a false sense of security. To address this, we implement and evaluate a password strength scoring system by comparing four machine learning models: Random Forest (RF), Support Vector Machine (SVM), a Convolutional Neural Network (CNN), and Logistic Regression with a dataset of over 660,000 real-world passwords. Our primary contribution is a novel hybrid feature engineering approach that captures nuanced vulnerabilities missed by standard metrics. We introduce features like leetspeak-normalized Shannon entropy to assess true randomness, pattern detection for keyboard walks and sequences, and character-level TF-IDF n-grams to identify frequently reused substrings from breached password datasets. our RF model achieved superior performance, achieving 99.12% accuracy on a held-out test set. Crucially, the interpretability of the Random Forest model allows for feature importance analysis, providing a clear pathway to developing security tools that offer specific, actionable feedback to users. This study bridges the gap between predictive accuracy and practical usability, resulting in a high-performance scoring system that not only reduces password-based vulnerabilities but also empowers users to make more informed security decisions.

cs.CR↗

An explainable Recursive Feature Elimination to detect Advanced Persistent Threats using Random Forest classifier

Intrusion Detection Systems (IDS) play a vital role in modern cybersecurity frameworks by providing a primary defense mechanism against sophisticated threat actors. In this paper, we propose an explainable intrusion detection framework that integrates Recursive Feature Elimination (RFE) with Random Forest (RF) to enhance detection of Advanced Persistent Threats (APTs). By using CICIDS2017 dataset, the approach begins with comprehensive data preprocessing and narrows down the most significant features via RFE. A Random Forest (RF) model was trained on the refined feature set, with SHapley Additive exPlanations (SHAP) used to interpret the contribution of each selected feature. Our experiment demonstrates that the explainable RF-RFE achieved a detection accuracy of 99.9%, reducing false positive and computational cost in comparison to traditional classifiers. The findings underscore the effectiveness of integrating explainable AI and feature selection to develop a robust, transparent, and deployable IDS solution.

cs.CR↗

Detecting Hope, Hate, and Emotion in Arabic Textual Speech and Multi-modal Memes Using Large Language Models

The rise of social media and online communication platforms has led to the spread of Arabic textual posts and memes as a key form of digital expression. While these contents can be humorous and informative, they are also increasingly being used to spread offensive language and hate speech. Consequently, there is a growing demand for precise analysis of content in Arabic text and memes. This paper explores the potential of large language models to effectively identify hope, hate speech, offensive language, and emotional expressions within such content. We evaluate the performance of base LLMs, fine-tuned LLMs, and pre-trained embedding models. The evaluation is conducted using a dataset of Arabic textual speech and memes proposed in the ArabicNLP MAHED 2025 challenge. The results underscore the capacity of LLMs such as GPT-4o-mini, fine-tuned with Arabic textual speech, and Gemini Flash 2.5, fine-tuned with Arabic memes, to deliver the superior performance. They achieve up to 72.1%, 57.8%, and 79.6% macro F1 scores for tasks 1, 2, and 3, respectively, and secure first place overall in the Mahed 2025 challenge. The proposed solutions offer a more nuanced understanding of both text and memes for accurate and efficient Arabic content moderation systems.

cs.CL↗

Benchmarking the Legal Reasoning of LLMs in Arabic Islamic Inheritance Cases

Islamic inheritance domain holds significant importance for Muslims to ensure fair distribution of shares between heirs. Manual calculation of shares under numerous scenarios is complex, time-consuming, and error-prone. Recent advancements in Large Language Models (LLMs) have sparked interest in their potential to assist with complex legal reasoning tasks. This study evaluates the reasoning capabilities of state-of-the-art LLMs to interpret and apply Islamic inheritance laws. We utilized the dataset proposed in the ArabicNLP QIAS 2025 challenge, which includes inheritance case scenarios given in Arabic and derived from Islamic legal sources. Various base and fine-tuned models, are assessed on their ability to accurately identify heirs, compute shares, and justify their reasoning in alignment with Islamic legal principles. Our analysis reveals that the proposed majority voting solution, leveraging three base models (Gemini Flash 2.5, Gemini Pro 2.5, and GPT o3), outperforms all other models that we utilized across every difficulty level. It achieves up to 92.7% accuracy and secures the third place overall in Task 1 of the Qias 2025 challenge.

cs.CL↗

Benchmarking the Medical Understanding and Reasoning of Large Language Models in Arabic Healthcare Tasks

Recent progress in large language models (LLMs) has showcased impressive proficiency in numerous Arabic natural language processing (NLP) applications. Nevertheless, their effectiveness in Arabic medical NLP domains has received limited investigation. This research examines the degree to which state-of-the-art LLMs demonstrate and articulate healthcare knowledge in Arabic, assessing their capabilities across a varied array of Arabic medical tasks. We benchmark several LLMs using a medical dataset proposed in the Arabic NLP AraHealthQA challenge in MedArabiQ2025 track. Various base LLMs were assessed on their ability to accurately provide correct answers from existing choices in multiple-choice questions (MCQs) and fill-in-the-blank scenarios. Additionally, we evaluated the capacity of LLMs in answering open-ended questions aligned with expert answers. Our results reveal significant variations in correct answer prediction accuracy and low variations in semantic alignment of generated answers, highlighting both the potential and limitations of current LLMs in Arabic clinical contexts. Our analysis shows that for MCQs task, the proposed majority voting solution, leveraging three base models (Gemini Flash 2.5, Gemini Pro 2.5, and GPT o3), outperforms others, achieving up to 77% accuracy and securing first place overall in the Arahealthqa 2025 shared task-track 2 (sub-task 1) challenge. Moreover, for the open-ended questions task, several LLMs were able to demonstrate excellent performance in terms of semantic alignment and achieve a maximum BERTScore of 86.44%.

cs.CL↗

Empowering the Grid: Collaborative Edge Artificial Intelligence for Decentralized Energy Systems

This paper examines how decentralized energy systems can be enhanced using collaborative Edge Artificial Intelligence. Decentralized grids use local renewable sources to reduce transmission losses and improve energy security. Edge AI enables real-time, privacy-preserving data processing at the network edge. Techniques such as federated learning and distributed control improve demand response, equipment maintenance, and energy optimization. The paper discusses key challenges including data privacy, scalability, and interoperability, and suggests solutions such as blockchain integration and adaptive architectures. Examples from virtual power plants and smart grids highlight the potential of these technologies. The paper calls for increased investment, policy support, and collaboration to advance sustainable energy systems.

cs.ET↗

Neutralizing the Narrative: AI-Powered Debiasing of Online News Articles

Bias in news reporting significantly impacts public perception, particularly regarding crime, politics, and societal issues. Traditional bias detection methods, predominantly reliant on human moderation, suffer from subjective interpretations and scalability constraints. Here, we introduce an AI-driven framework leveraging advanced large language models (LLMs), specifically GPT-4o, GPT-4o Mini, Gemini Pro, Gemini Flash, Llama 8B, and Llama 3B, to systematically identify and mitigate biases in news articles. To this end, we collect an extensive dataset consisting of over 30,000 crime-related articles from five politically diverse news sources spanning a decade (2013-2023). Our approach employs a two-stage methodology: (1) bias detection, where each LLM scores and justifies biased content at the paragraph level, validated through human evaluation for ground truth establishment, and (2) iterative debiasing using GPT-4o Mini, verified by both automated reassessment and human reviewers. Empirical results indicate GPT-4o Mini's superior accuracy in bias detection and effectiveness in debiasing. Furthermore, our analysis reveals temporal and geographical variations in media bias correlating with socio-political dynamics and real-world events. This study contributes to scalable computational methodologies for bias mitigation, promoting fairness and accountability in news reporting.

cs.CL↗

Self-Reflection Makes Large Language Models Safer, Less Biased, and Ideologically Neutral

Previous studies proposed that the reasoning capabilities of large language models (LLMs) can be improved through self-reflection, i.e., letting LLMs reflect on their own output to identify and correct mistakes in the initial responses. However, earlier experiments offer mixed results when it comes to the benefits of self-reflection. Furthermore, prior studies on self-reflection are predominantly concerned with the reasoning capabilities of models, ignoring the potential for self-reflection in safety, bias, and ideological leaning. Here, by conducting a series of experiments testing LLM's self-reflection capability in various tasks using a variety of prompts and different LLMs, we make several contributions to the literature. First, we reconcile conflicting findings regarding the benefit of self-reflection, by demonstrating that the outcome of self-reflection is sensitive to prompt wording -- both the original prompt that are used to elicit an initial answer and the subsequent prompt used to self-reflect. Specifically, although self-reflection may improve the reasoning capability of LLMs when the initial response is simple, the technique cannot improve upon the state-of-the-art chain-of-thought (CoT) prompting. Second, we show that self-reflection can lead to safer (75.8\% reduction in toxic responses while preserving 97.8\% non-toxic ones), less biased (77\% reduction in gender biased responses, while preserving 94.3\% unbiased ones), and more ideologically neutral responses (100\% reduction in partisan leaning response, while preserving 87.7\% non-partisan ones). The paper concludes by discussing the implications of our findings on the deployment of large language models. We release our experiments at https://github.com/Michael98Liu/self-reflection.

cs.CL↗

A Conceptual Exploration of Generative AI-Induced Cognitive Dissonance and its Emergence in University-Level Academic Writing

The integration of Generative Artificial Intelligence (GenAI) into university-level academic writing presents both opportunities and challenges, particularly in relation to cognitive dissonance (CD). This work explores how GenAI serves as both a trigger and amplifier of CD, as students navigate ethical concerns, academic integrity, and self-efficacy in their writing practices. By synthesizing empirical evidence and theoretical insights, we introduce a hypothetical construct of GenAI-induced CD, illustrating the psychological tension between AI-driven efficiency and the principles of originality, effort, and intellectual ownership. We further discuss strategies to mitigate this dissonance, including reflective pedagogy, AI literacy programs, transparency in GenAI use, and discipline-specific task redesigns. These approaches reinforce critical engagement with AI, fostering a balanced perspective that integrates technological advancements while safeguarding human creativity and learning. Our findings contribute to ongoing discussions on AI in education, self-regulated learning, and ethical AI use, offering a conceptual framework for institutions to develop guidelines that align AI adoption with academic values.

cs.CY↗

Advancing Vehicle Plate Recognition: Multitasking Visual Language Models with VehiclePaliGemma

License plate recognition (LPR) involves automated systems that utilize cameras and computer vision to read vehicle license plates. Such plates collected through LPR can then be compared against databases to identify stolen vehicles, uninsured drivers, crime suspects, and more. The LPR system plays a significant role in saving time for institutions such as the police force. In the past, LPR relied heavily on Optical Character Recognition (OCR), which has been widely explored to recognize characters in images. Usually, collected plate images suffer from various limitations, including noise, blurring, weather conditions, and close characters, making the recognition complex. Existing LPR methods still require significant improvement, especially for distorted images. To fill this gap, we propose utilizing visual language models (VLMs) such as OpenAI GPT4o, Google Gemini 1.5, Google PaliGemma (Pathways Language and Image model + Gemma model), Meta Llama 3.2, Anthropic Claude 3.5 Sonnet, LLaVA, NVIDIA VILA, and moondream2 to recognize such unclear plates with close characters. This paper evaluates the VLM's capability to address the aforementioned problems. Additionally, we introduce ``VehiclePaliGemma'', a fine-tuned Open-sourced PaliGemma VLM designed to recognize plates under challenging conditions. We compared our proposed VehiclePaliGemma with state-of-the-art methods and other VLMs using a dataset of Malaysian license plates collected under complex conditions. The results indicate that VehiclePaliGemma achieved superior performance with an accuracy of 87.6\%. Moreover, it is able to predict the car's plate at a speed of 7 frames per second using A100-80GB GPU. Finally, we explored the multitasking capability of VehiclePaliGemma model to accurately identify plates containing multiple cars of various models and colors, with plates positioned and oriented in different directions.

cs.CV↗