arXiv subjects

Adnan Mahmood

Publications and source records attributed to Adnan Mahmood.

At least 19 recordsLinked to original sources

arXiv2026

Can We Trust Video Hallucination Detectors? VidHalLoc for Evaluating the Evaluators

Video-language models and video agents can produce hallucinations that conflict with spatiotemporal evidence. Existing benchmarks mainly evaluate model hallucinations, and heterogeneous mechanisms make detector reliability difficult to compare. We introduce VidHalLoc, a benchmark that evaluates hallucination detection methods under a unified diagnostic evaluation protocol using 2,000 adversarial hallucination samples across Video Question Answering and Video Captioning tasks, spanning Ontology and Dynamic hallucination categories. To construct VidHalLoc efficiently, we introduce VideoHALO, a Harness Engineering-informed multi-agent workflow that decomposes data construction into four executable stages supported by a memory system and a communication protocol. Evaluation of fifteen methods reveals that the four dedicated detectors peak at an Overall accuracy of only 34.63%, indicating limited reliability across video hallucination types [Dataset Repository: https://huggingface.co/datasets/wesfggfd/VidHalLoc].

cs.CV↗

arXiv2026

When Confidence Fails: Overconfidence in LLMs under Uncertainty and Missing Clinical Information

Large Language Models (LLMs) have achieved strong performance in medical question answering and clinical reasoning tasks. However, their reliability under uncertainty remains poorly understood which raises critical concerns for deployment in high-stakes clinical settings. In such environments, incorrect predictions are inherently risky, but confident incorrect predictions can be particularly harmful as they may mislead clinical decision-making. In this paper, we conduct a systematic behavioral analysis of LLMs under clinical information uncertainty. We propose an evaluation framework based on the MedMCQA dataset consisting of two complementary uncertainty settings. First, we introduce linguistic uncertainty cues through prompt modifications to simulate ambiguous clinical contexts. Second, we construct an answer removal setting, wherein the correct option is deliberately excluded mandating the model to recognize insufficient information and abstain. We analyze both model accuracy and confidence behavior using multiple calibration metrics including calibration gap, Expected Calibration Error (ECE), and Unsafe Confident Error Rate (UCER) across 500 medical questions. Our results reveal a consistent failure mode, i.e., although accuracy degrades under increasing uncertainty, model confidence remains misaligned with accuracy. This leads to a substantial increase in unsafe confident errors, indicating that model confidence remains largely insensitive to clinically meaningful information loss. Furthermore, we observe significant variation across models in their ability to abstain when the correct answer is unavailable, with some models persistently producing high confidence hallucinated answers. These findings expose critical limitations in the epistemic reliability of current LLMs and highlight the need for uncertainty aware evaluation methods prior to their deployment in clinical workflows.

cs.CL↗

arXiv2026

Learning Color Grading, No Photo Sharing: Federated Aesthetic Preference Learning for Personalized Image Enhancement

Personalized image enhancement should reflect individual aesthetic taste, yet learning such preferences commonly depends on private photos and ratings that are unsuitable for centralized collection. The task must infer preference from sparse, heterogeneous feedback and translate it into natural-looking color transformations on resource-constrained user devices. We introduce FedPAIE, a federated personalized aesthetic image enhancement framework for user-adaptive color grading without centralizing raw photos or ratings. FedPAIE trains a lightweight dual-cue aesthetic scorer, calibrates it into a personalized scorer on a small local support set, and freezes it to guide regularized adaptation of a lightweight CLUT enhancer from unpaired local photographs. Fidelity constraints and an excess-gap penalty regularize scorer-guided adaptation to limit proxy-score over-optimization while preserving content and natural appearance. Training remains lightweight throughout the pipeline: scorer learning updates at most 0.787M parameters, enhancer adaptation updates 0.265M, and inference retains only a 0.293M-parameter personalized enhancer. Experiments on MIT-Adobe FiveK and Flickr-AES demonstrate effective open-world personalization and a favorable balance between user preference and image fidelity. FedPAIE thus connects decentralized preference learning with efficient personalized image transformation without requiring paired user retouches.

cs.CV↗

arXiv2026

AgenticAI-DialogGen: Topic-Guided Conversation Generation for Fine-Tuning and Evaluating Short- and Long-Term Memories of LLMs

Recent advancements in Large Language Models (LLMs) have improved their ability to process extended conversational contexts, yet fine-tuning and evaluating short- and long-term memories remain difficult due to the absence of datasets that encode both short- and long-term conversational history. Existing conversational datasets lack memory grounding, overlook topic continuity, or rely on costly human annotation. To address these gaps, we introduce AgenticAI-DialogGen, a modular agent-based framework that generates persona-grounded and topic-guided conversations without human supervision. The framework uses LLM agents to extract knowledge graphs, identify topics, build speaker personas, and simulate topic-guided conversations from unstructured conversations. A QA module generates memory-grounded Question Answer (QA) pairs drawn from short- and long-term conversational histories. We also generated a new dataset entitled, TopicGuidedChat (TGC), where long-term memory is encoded as speaker-specific knowledge graphs and short-term memory as newly generated topic-guided conversations. Evaluations depict that AgenticAI-DialogGen yields higher conversational quality and LLMs fine-tuned on TGC dataset achieve improved performance on memory-grounded QA tasks.

cs.CL↗

arXiv2026

CoRe-Fed: Bridging Collaborative and Representation Fairness via Federated Embedding Distillation

With the proliferation of distributed data sources, Federated Learning (FL) has emerged as a key approach to enable collaborative intelligence through decentralized model training while preserving data privacy. However, conventional FL algorithms often suffer from performance disparities across clients caused by heterogeneous data distributions and unequal participation, which leads to unfair outcomes. Specifically, we focus on two core fairness challenges, i.e., representation bias, arising from misaligned client representations, and collaborative bias, stemming from inequitable contribution during aggregation, both of which degrade model performance and generalizability. To mitigate these disparities, we propose CoRe-Fed, a unified optimization framework that bridges collaborative and representation fairness via embedding-level regularization and fairness-aware aggregation. Initially, an alignment-driven mechanism promotes semantic consistency between local and global embeddings to reduce representational divergence. Subsequently, a dynamic reward-penalty-based aggregation strategy adjusts each client's weight based on participation history and embedding alignment to ensure contribution-aware aggregation. Extensive experiments across diverse models and datasets demonstrate that CoRe-Fed improves both fairness and model performance over the state-of-the-art baseline algorithms.

cs.LG↗

arXiv2026

Federated Learning at the Forefront of Fairness: A Multifaceted Perspective

Fairness in Federated Learning (FL) is emerging as a critical factor driven by heterogeneous clients' constraints and balanced model performance across various scenarios. In this survey, we delineate a comprehensive classification of the state-of-the-art fairness-aware approaches from a multifaceted perspective, i.e., model performance-oriented and capability-oriented. Moreover, we provide a framework to categorize and address various fairness concerns and associated technical aspects, examining their effectiveness in balancing equity and performance within FL frameworks. We further examine several significant evaluation metrics leveraged to measure fairness quantitatively. Finally, we explore exciting open research directions and propose prospective solutions that could drive future advancements in this important area, laying a solid foundation for researchers working toward fairness in FL.

cs.LG↗

arXiv2025

FedVideoMAE: Efficient Privacy-Preserving Federated Video Moderation

Short-form video moderation increasingly needs learning pipelines that protect user privacy without paying the full bandwidth and latency cost of cloud-centralized inference. We present FedVideoMAE, an on-device federated framework for video violence detection that combines self-supervised VideoMAE representations, LoRA-based parameter-efficient adaptation, client-side DP-SGD, and server-side secure aggregation. By updating only 5.5M parameters (about 3.5% of a 156M backbone), FedVideoMAE reduces communication by 28.3x relative to full-model federated updates while keeping raw videos on device throughout training. On RWF-2000 with 40 clients, the method reaches 77.25% accuracy without privacy protection and 65~66% under strong differential privacy. We further show that this privacy gap is consistent with an effective-SNR analysis tailored to the small-data, parameter-efficient federated regime, which indicates roughly 8.5~12x DP-noise amplification in our setting. To situate these results more clearly, we also compare against archived full-model federated baselines and summarize auxiliary transfer behavior on RLVS and binary UCF-Crime. Taken together, these findings position FedVideoMAE as a practical operating point for privacy-preserving video moderation on edge devices. Our code can be found at: https://github.com/zyt-599/FedVideoMAE.

cs.CV↗

arXiv2025

FedCLF -- Towards Efficient Participant Selection for Federated Learning in Heterogeneous IoV Networks

Federated Learning (FL) is a distributed machine learning technique that preserves data privacy by sharing only the trained parameters instead of the client data. This makes FL ideal for highly dynamic, heterogeneous, and time-critical applications, in particular, the Internet of Vehicles (IoV) networks. However, FL encounters considerable challenges in such networks owing to the high data and device heterogeneity. To address these challenges, we propose FedCLF, i.e., FL with Calibrated Loss and Feedback control, which introduces calibrated loss as a utility in the participant selection process and a feedback control mechanism to dynamically adjust the sampling frequency of the clients. The envisaged approach (a) enhances the overall model accuracy in case of highly heterogeneous data and (b) optimizes the resource utilization for resource constrained IoV networks, thereby leading to increased efficiency in the FL process. We evaluated FedCLF vis-\`a-vis baseline models, i.e., FedAvg, Newt, and Oort, using CIFAR-10 dataset with varying data heterogeneity. Our results depict that FedCLF significantly outperforms the baseline models by up to a 16% improvement in high data heterogeneity-related scenarios with improved efficiency via reduced sampling frequency.

cs.LG↗

arXiv2025

FairEquityFL -- A Fair and Equitable Client Selection in Federated Learning for Heterogeneous IoV Networks

Federated Learning (FL) has been extensively employed for a number of applications in machine learning, i.e., primarily owing to its privacy preserving nature and efficiency in mitigating the communication overhead. Internet of Vehicles (IoV) is one of the promising applications, wherein FL can be utilized to train a model more efficiently. Since only a subset of the clients can participate in each FL training round, challenges arise pertinent to fairness in the client selection process. Over the years, a number of researchers from both academia and industry have proposed numerous FL frameworks. However, to the best of our knowledge, none of them have employed fairness for FL-based client selection in a dynamic and heterogeneous IoV environment. Accordingly, in this paper, we envisage a FairEquityFL framework to ensure an equitable opportunity for all the clients to participate in the FL training process. In particular, we have introduced a sampling equalizer module within the selector component for ensuring fairness in terms of fair collaboration opportunity for all the clients in the client selection process. The selector is additionally responsible for both monitoring and controlling the clients' participation in each FL training round. Moreover, an outlier detection mechanism is enforced for identifying malicious clients based on the model performance in terms of considerable fluctuation in either accuracy or loss minimization. The selector flags suspicious clients and temporarily suspend such clients from participating in the FL training process. We further evaluate the performance of FairEquityFL on a publicly available dataset, FEMNIST. Our simulation results depict that FairEquityFL outperforms baseline models to a considerable extent.

cs.LG↗

arXiv2025

Towards Adaptive Context Management for Intelligent Conversational Question Answering

This particular paper introduces an Adaptive Context Management (ACM) framework for the Conversational Question Answering (ConvQA) systems. The key objective of the ACM framework is to optimize the use of the conversation history by dynamically managing context for maximizing the relevant information provided to a ConvQA model within its token limit. Our approach incorporates a Context Manager (CM) Module, a Summarization (SM) Module, and an Entity Extraction (EE) Module in a bid to handle the conversation history efficaciously. The CM Module dynamically adjusts the context size, thereby preserving the most relevant and recent information within a model's token limit. The SM Module summarizes the older parts of the conversation history via a sliding window. When the summarization window exceeds its limit, the EE Module identifies and retains key entities from the oldest conversation turns. Experimental results demonstrate the effectiveness of our envisaged framework in generating accurate and contextually appropriate responses, thereby highlighting the potential of the ACM framework to enhance the robustness and scalability of the ConvQA systems.

cs.CL↗

arXiv2025

A Survey of the State-of-the-Art in Conversational Question Answering Systems

Conversational Question Answering (ConvQA) systems have emerged as a pivotal area within Natural Language Processing (NLP) by driving advancements that enable machines to engage in dynamic and context-aware conversations. These capabilities are increasingly being applied across various domains, i.e., customer support, education, legal, and healthcare where maintaining a coherent and relevant conversation is essential. Building on recent advancements, this survey provides a comprehensive analysis of the state-of-the-art in ConvQA. This survey begins by examining the core components of ConvQA systems, i.e., history selection, question understanding, and answer prediction, highlighting their interplay in ensuring coherence and relevance in multi-turn conversations. It further investigates the use of advanced machine learning techniques, including but not limited to, reinforcement learning, contrastive learning, and transfer learning to improve ConvQA accuracy and efficiency. The pivotal role of large language models, i.e., RoBERTa, GPT-4, Gemini 2.0 Flash, Mistral 7B, and LLaMA 3, is also explored, thereby showcasing their impact through data scalability and architectural advancements. Additionally, this survey presents a comprehensive analysis of key ConvQA datasets and concludes by outlining open research directions. Overall, this work offers a comprehensive overview of the ConvQA landscape and provides valuable insights to guide future advancements in the field.

cs.CL↗

arXiv2025

Fairness in Federated Learning: Trends, Challenges, and Opportunities

At the intersection of the cutting-edge technologies and privacy concerns, Federated Learning (FL) with its distributed architecture, stands at the forefront in a bid to facilitate collaborative model training across multiple clients while preserving data privacy. However, the applicability of FL systems is hindered by fairness concerns arising from numerous sources of heterogeneity that can result in biases and undermine a system's effectiveness, with skewed predictions, reduced accuracy, and inefficient model convergence. This survey thus explores the diverse sources of bias, including but not limited to, data, client, and model biases, and thoroughly discusses the strengths and limitations inherited within the array of the state-of-the-art techniques utilized in the literature to mitigate such disparities in the FL training process. We delineate a comprehensive overview of the several notions, theoretical underpinnings, and technical aspects associated with fairness and their adoption in FL-based multidisciplinary environments. Furthermore, we examine salient evaluation metrics leveraged to measure fairness quantitatively. Finally, we envisage exciting open research directions that have the potential to drive future advancements in achieving fairer FL frameworks, in turn, offering a strong foundation for future research in this pivotal area.

cs.LG↗

arXiv2023

When Large Language Models Meet Citation: A Survey

Citations in scholarly work serve the essential purpose of acknowledging and crediting the original sources of knowledge that have been incorporated or referenced. Depending on their surrounding textual context, these citations are used for different motivations and purposes. Large Language Models (LLMs) could be helpful in capturing these fine-grained citation information via the corresponding textual context, thereby enabling a better understanding towards the literature. Furthermore, these citations also establish connections among scientific papers, providing high-quality inter-document relationships and human-constructed knowledge. Such information could be incorporated into LLMs pre-training and improve the text representation in LLMs. Therefore, in this paper, we offer a preliminary review of the mutually beneficial relationship between LLMs and citation analysis. Specifically, we review the application of LLMs for in-text citation analysis tasks, including citation classification, citation-based summarization, and citation recommendation. We then summarize the research pertinent to leveraging citation linkage knowledge to improve text representations of LLMs via citation prediction, network structure information, and inter-document relationship. We finally provide an overview of these contemporary methods and put forth potential promising avenues in combining LLMs and citation analysis for further investigation.

cs.DL↗

arXiv2023

Learning to Select the Relevant History Turns in Conversational Question Answering

The increasing demand for the web-based digital assistants has given a rapid rise in the interest of the Information Retrieval (IR) community towards the field of conversational question answering (ConvQA). However, one of the critical aspects of ConvQA is the effective selection of conversational history turns to answer the question at hand. The dependency between relevant history selection and correct answer prediction is an intriguing but under-explored area. The selected relevant context can better guide the system so as to where exactly in the passage to look for an answer. Irrelevant context, on the other hand, brings noise to the system, thereby resulting in a decline in the model's performance. In this paper, we propose a framework, DHS-ConvQA (Dynamic History Selection in Conversational Question Answering), that first generates the context and question entities for all the history turns, which are then pruned on the basis of similarity they share in common with the question at hand. We also propose an attention-based mechanism to re-rank the pruned terms based on their calculated weights of how useful they are in answering the question. In the end, we further aid the model by highlighting the terms in the re-ranked conversational history using a binary classification task and keeping the useful terms (predicted as 1) and ignoring the irrelevant terms (predicted as 0). We demonstrate the efficacy of our proposed framework with extensive experimental results on CANARD and QuAC -- the two popularly utilized datasets in ConvQA. We demonstrate that selecting relevant turns works better than rewriting the original question. We also investigate how adding the irrelevant history turns negatively impacts the model's performance and discuss the research challenges that demand more attention from the IR community.

cs.CL↗

arXiv2023

Can we Quantify Trust? Towards a Trust-based Resilient SIoT Network

The emerging yet promising paradigm of the Social Internet of Things (SIoT) integrates the notion of the Internet of Things with human social networks. In SIoT, objects, i.e., things, have the capability to socialize with the other objects in the SIoT network and can establish their social network autonomously by modeling human behaviour. The notion of trust is imperative in realizing these characteristics of socialization in order to assess the reliability of autonomous collaboration. The perception of trust is evolving in the era of SIoT as an extension to traditional security triads in an attempt to offer secure and reliable services, and is considered as an imperative aspect of any SIoT system for minimizing the probable risk of autonomous decision-making. This research investigates the idea of trust quantification by employing trust measurement in terms of direct trust, indirect trust as a recommendation, and the degree of SIoT relationships in terms of social similarities (community-of-interest, friendship, and co-work relationships). A weighted sum approach is subsequently employed to synthesize all the trust features in order to ascertain a single trust score. The experimental evaluation demonstrates the effectiveness of the proposed model in segregating trustworthy and untrustworthy objects and via identifying the dynamic behaviour (i.e., trust-related attacks) of the SIoT objects.

cs.CR↗

arXiv2023

Keeping the Questions Conversational: Using Structured Representations to Resolve Dependency in Conversational Question Answering

Having an intelligent dialogue agent that can engage in conversational question answering (ConvQA) is now no longer limited to Sci-Fi movies only and has, in fact, turned into a reality. These intelligent agents are required to understand and correctly interpret the sequential turns provided as the context of the given question. However, these sequential questions are sometimes left implicit and thus require the resolution of some natural language phenomena such as anaphora and ellipsis. The task of question rewriting has the potential to address the challenges of resolving dependencies amongst the contextual turns by transforming them into intent-explicit questions. Nonetheless, the solution of rewriting the implicit questions comes with some potential challenges such as resulting in verbose questions and taking conversational aspect out of the scenario by generating self-contained questions. In this paper, we propose a novel framework, CONVSR (CONVQA using Structured Representations) for capturing and generating intermediate representations as conversational cues to enhance the capability of the QA model to better interpret the incomplete questions. We also deliberate how the strengths of this task could be leveraged in a bid to design more engaging and eloquent conversational agents. We test our model on the QuAC and CANARD datasets and illustrate by experimental results that our proposed framework achieves a better F1 score than the standard question rewriting model.

cs.CL↗

arXiv2022

A Survey on Participant Selection for Federated Learning in Mobile Networks

Federated Learning (FL) is an efficient distributed machine learning paradigm that employs private datasets in a privacy-preserving manner. The main challenges of FL is that end devices usually possess various computation and communication capabilities and their training data are not independent and identically distributed (non-IID). Due to limited communication bandwidth and unstable availability of such devices in a mobile network, only a fraction of end devices (also referred to as the participants or clients in a FL process) can be selected in each round. Hence, it is of paramount importance to utilize an efficient participant selection scheme to maximize the performance of FL including final model accuracy and training time. In this paper, we provide a review of participant selection techniques for FL. First, we introduce FL and highlight the main challenges during participant selection. Then, we review the existing studies and categorize them based on their solutions. Finally, we provide some future directions on participant selection for FL based on our analysis of the state-of-the-art in this topic area.

cs.DC↗

arXiv2022

GCN-based Multi-task Representation Learning for Anomaly Detection in Attributed Networks

Anomaly detection in attributed networks has received a considerable attention in recent years due to its applications in a wide range of domains such as finance, network security, and medicine. Traditional approaches cannot be adopted on attributed networks' settings to solve the problem of anomaly detection. The main limitation of such approaches is that they inherently ignore the relational information between data features. With a rapid explosion in deep learning- and graph neural networks-based techniques, spotting rare objects on attributed networks has significantly stepped forward owing to the potentials of deep techniques in extracting complex relationships. In this paper, we propose a new architecture on anomaly detection. The main goal of designing such an architecture is to utilize multi-task learning which would enhance the detection performance. Multi-task learning-based anomaly detection is still in its infancy and only a few studies in the existing literature have catered to the same. We incorporate both community detection and multi-view representation learning techniques for extracting distinct and complementary information from attributed networks and subsequently fuse the captured information for achieving a better detection result. The mutual collaboration between two main components employed in this architecture, i.e., community-specific learning and multi-view representation learning, exhibits a promising solution to reach more effective results.

cs.LG↗