arXiv subjects

Elias Hossain

Publications and source records attributed to Elias Hossain.

18 recordsLinked to original sources

arXiv2026

BioDivergence: A Benchmark and Evaluation Framework for Hidden Contextual Contradictions in Biomedical Abstracts

Biomedical findings often seem to conflict across studies, but many of these differences are context-dependent rather than true contradictions. Variations in cohort, geography, assay protocol, disease subtype, and clinical setting can make both claims locally valid. Existing NLI and scientific claim-verification benchmarks reduce such cases to entailment, contradiction, or neutral, failing to capture the contextual structure behind divergence. To address this, we introduce BioDivergence, an evaluation framework with a six-class conflict taxonomy, a 13-axis divergence ontology, and four structured outputs per claim pair: conflict type, divergence axes, dominant confounder, and reconciliation explanation. We release BioDivergence-Silver-v1.0, an article-disjoint silver benchmark of 11,865 claim pairs across five biomedical domains, alongside a legacy deduplicated variant for comparison. Results show notable ranking differences between the two variants, with the fine-tuned reference model dropping about 12 points under the article-disjoint setting, while Mistral-7B-Instruct-v0.3 achieves 0.5523 accuracy and 0.3894 contextual-F1 on the 842-example primary test set. BioDivergence offers a more faithful way to distinguish contextual divergence from direct contradiction and to separate article-level memorization from genuine task learning.

cs.CL↗

arXiv2026

ChannelGuard: Safe Models Do Not Compose into Safe Multi-Agent Systems

Multi-agent LLM applications chain a planner, worker agents, a verifier, and a synthesizer, and every hop between agents is an unmonitored channel through which an adversary can smuggle instructions. Existing defenses guard only the input boundary (IBProtector, Llama Guard, perplexity filters, SmoothLLM) or run outside the application as opaque, stochastic provider-side filters. We show this gap carries a consequence rarely measured: on a 2,100-trace evaluation across eight attack families, five defenses, and three model backends, an undefended pipeline that appears fully safe under standard reporting (attack success 0.000 on tool- and memory-poisoning) owes that safety almost entirely to the cloud provider's server-side filter (54 of 60 blocks on Azure GPT-5), and silently shifts to the agent model's own alignment on a backend without such a filter. Outcome-only reporting hides this dependence. We present ChannelGuard, a training-free defense-in-depth framework placing information-bottleneck gates on every inter-agent channel; each scores channel text against an adversarial phrase bank by embedding similarity and deterministically passes, compresses, or blocks it, adding no LLM call, while an attribution method records which layer stopped each attack. ChannelGuard's tool-output gate blocks Tool Poisoning 30 of 30 at the application layer, identically across Azure GPT-5, Anthropic Sonnet 4.5, and Anthropic Haiku 4.5, whereas the undefended pipeline shifts entirely across backends; it also lowers Prompt Injection attack success by half (0.333 to 0.167) and preserves GSM8K accuracy exactly (0.867). White-box adaptive paraphrase evades every embedding gate, where a perturb-and-vote baseline does better. An extended appendix adds baselines, ablations, sweeps, a benign-preservation analysis, and a judge audit (kappa = 0.900), at a total cost of 47.36 USD.

cs.CR↗

arXiv2026

Right Knowledge, Wrong Answer: Characterizing Parametric Temporal Conflict in Open-Weight Language Models

Language models may encode both outdated facts and their newer replacements. We introduce Parametric Temporal Conflict (PTC), where the newer fact is present and recoverable, but the default forward pass prefers the outdated one. We release a deterministically verified benchmark of 8,746 Wikidata position-holder transitions and evaluate four open-weight language models across three families. A date-prefix prompt recovers the newer fact in 61-81% of PTC cases. Activation patching flips predictions in 72-85% of cases and localizes the preference to model-specific upper-layer regions. Residual-stream steering outperforms norm-matched random directions, indicating direction-specific representations. These results show that PTC reflects a localized representational preference rather than missing knowledge. Recovery is measured on oracle-identified conflicts because automatic detection remains unreliable. We release the benchmark, code, and statistics.

cs.LG↗

arXiv2026

MotifRole-Diff: Risk-Optimal Role-Aware Corruption for Masked Molecular Graph Diffusion

Masked discrete diffusion for molecular graph generation typically applies a uniform corruption schedule to all tokens in a lossless graph-to-sequence representation, implicitly treating structurally heterogeneous molecular components as equally difficult and equally important to reconstruct. However, different molecular graph token roles exhibit substantial variation in denoising difficulty and their influence on the decoded molecule, motivating role-specific corruption strategies. We introduce MotifRole-Diff, a role-aware corruption process that allocates masking rates according to empirically measured denoising difficulty and graph-level perturbation impact while preserving the model architecture, clean sequence space, and lossless molecular-graph decoder. We formulate schedule selection as the risk-optimal allocation of a fixed masking budget across token roles. Our theorem characterizes optimality for the modeled role-weighted residual risk, while downstream generation performance is evaluated empirically. Under matched architecture, training budget, and sampling compute, MotifRole-Diff improves validity on QM9 from 0.905 to 0.944 while reducing FCD from 1.701 to 1.609, and on MOSES improves validity from 0.920 to 0.938 while reducing FCD from 2.125 to 1.850. Role-wise diagnostics further show improved reconstruction across molecular graph token categories. Together, these matched-compute results indicate that structurally informed corruption is a more effective masking strategy than uniform schedules for serialized molecular graph diffusion.

cs.LG↗

arXiv2026

MedBayes-Lite: A Clinical Uncertainty Governance Layer for Risk-Aware Medical Decision Support

Clinical language models often assign high confidence to incorrect predictions, particularly in high-severity and out-of-distribution cases. We present MedBayes-Lite, a retraining-free uncertainty governance layer for transformer-based clinical predictors. It combines Monte Carlo dropout, predictive calibration, and confidence-guided abstention to defer low-confidence predictions for human review, adding no trainable parameters. Evaluated on MedMCQA and MedQA-USMLE, MedBayes-Lite reduces expected calibration error by 0.23 to 0.33 and drives harmful overconfident errors (confident, incorrect, high-severity predictions) toward zero. Under domain shift from MedMCQA to MedQA-USMLE, it reduces confident high-severity errors from about 21% to near zero while roughly halving calibration drift. We also introduce the Clinical Uncertainty Score (CUS), which strongly correlates with harmful overconfidence (r approximately 0.88). Although the framework does not improve risk-coverage ranking, and temperature scaling or deep ensembles may provide advantages in calibration cost or risk ranking, MedBayes-Lite offers a practical calibration-and-abstention layer that reduces confident high-severity errors in clinical question-answering benchmarks.

cs.AI↗

arXiv2026

NEXUS: Structured Runtime Safety for Tool-Using LLM Agents

Tool-using LLM agents increasingly execute high-impact actions, making runtime safety monitoring essential. We present NEXUS (Neural EXecution Utility and Safety), a structured-plan safety monitor that applies a formal intervention policy to select among four actions: allow, block, request confirmation, or request revision. NEXUS combines deterministic safety rules, argument-level inspection, and a calibrated logistic-regression risk score for graded escalation. On a 128-instance synthetic benchmark, NEXUS achieves an F1 score of 0.949 and a 4-class intervention accuracy of 0.6406, outperforming rule-only intervention selection by 27.3 percentage points. It also improves over rule-only on R-Judge (F1 = 0.861 vs. 0.849), matches rule-only on AgentHarm due to threat-model limits, and achieves 0% ASR at 99% control allow on IPI. On the rule-blind NEXUS-Stress benchmark, NEXUS reaches an F1 score of 0.881, highlighting the difficulty of fine-grained intervention routing. With 0.205 ms median latency, NEXUS adds under 0.1% overhead to typical agent loops. Code, benchmarks, and the calibrated risk scorer are publicly released.

cs.AI↗

arXiv2026

Learning Stable Predictors from Weak Supervision under Distribution Shift

Learning from weak, proxy, or relative supervision is common when ground-truth labels are unavailable, but robustness under distribution shift remains poorly understood because the supervision mechanism itself may change across environments. We formalize this phenomenon as supervision drift, defined as changes in $P(y \mid x, c)$ across contexts, and study it in CRISPR-Cas13d transcriptomic perturbation experiments where guide efficacy is inferred indirectly from RNA-seq responses. Using publicly available data spanning two human cell lines and multiple post-induction timepoints, we construct a controlled non-IID benchmark with explicit domain (cell line) and temporal shifts, while reusing a fixed weak-label construction across all contexts to avoid changing targets. Across linear and tree-based models, weak supervision supports meaningful learning in-domain (ridge $R^2 = 0.356$, Spearman $ρ= 0.442$) and partial cross-cell-line transfer ($ρ\approx 0.40$). In contrast, temporal transfer collapses across all model classes considered, yielding negative $R^2$ and weak or near-zero $ρ$ (ridge $R^2 = -0.145$, $ρ= 0.008$; XGBoost $R^2 = -0.155$, $ρ= 0.056$; random forest $R^2 = -0.322$, $ρ= 0.139$). Additional robustness analyses using externally recomputed weak labels, shift-score quantification, and simple mitigation baselines preserve the same qualitative pattern. Feature-label association and feature-importance analyses remain relatively stable across cell lines but change sharply over time, indicating that failures arise from supervision drift rather than model capacity or simple covariate shift. These results show that strong in-domain performance under weak supervision can be misleading and motivate feature stability as a lightweight diagnostic for non-transferability before deployment.

cs.LG↗

arXiv2026

When Policies Cannot Be Retrained: A Unified Closed-Form View of Post-Training Steering in Offline Reinforcement Learning

Offline reinforcement learning (RL) can learn effective policies from fixed datasets, but deployment objectives may change after training, and in many applications the trained actor cannot be retrained because of data, cost, or governance constraints. We study deployment-time adaptation for frozen offline actors using Product-of-Experts (PoE) composition with a goal-conditioned prior. Our main practical finding is graceful degradation rather than universal performance gain: under degraded or random priors, precision-weighted composition remains anchored to the frozen actor, while additive and prior-only adaptation collapse, and a KL-budget selector often recovers a near-oracle operating point. We also make explicit a closed-form identity in the frozen-actor setting: for diagonal-Gaussian actors and priors, PoE with coefficient alpha yields the same deterministic policy as KL-regularized adaptation with beta = alpha / (1 - alpha), with posterior covariances differing only by a global scalar factor. Empirically, across four D4RL environments (3,900 MuJoCo episodes), we observe a 4/5/3 HELP/FROZEN/HURT split. Extending the analysis to six harder cells and two AntMaze diagnostics reveals an actor-competence ceiling: medium-expert remains HURT in all 9 cells at every tested alpha, while AntMaze with a behavior-cloned frozen actor yields zero success for all composition rules. Overall, PoE and KL-regularized adaptation are best viewed as a single actor-anchored safety mechanism for deployment-time steering.

cs.LG↗

arXiv2026

BIOGEN: Evidence-Grounded Multi-Agent Reasoning Framework for Transcriptomic Interpretation in Antimicrobial Resistance

Interpreting gene clusters from RNA sequencing (RNA-seq) remains challenging, especially in antimicrobial resistance studies where mechanistic insight is important for hypothesis generation. Existing pathway enrichment methods can summarize co-expressed modules, but they often provide limited cluster-specific explanations and weak connections to supporting literature. We present BIOGEN, an evidence-grounded multi-agent framework for post hoc interpretation of RNA-seq transcriptional modules. BIOGEN combines biomedical retrieval, structured reasoning, and multi-critic verification to generate traceable cluster-level explanations with explicit evidence and confidence labels. On a primary Salmonella enterica dataset, BIOGEN achieved strong biological grounding, including BERTScore 0.689, Semantic Alignment Score 0.715, KEGG Functional Similarity 0.342, and a hallucination rate of 0.000, compared with 0.100 for an LLM-only baseline. Across four additional bacterial RNA-seq datasets, BIOGEN also maintained zero hallucination under the same fixed pipeline. In comparisons with representative open-source agentic AI baselines, BIOGEN was the only framework that consistently preserved zero hallucination across all five datasets. These findings suggest that retrieval alone is not enough for reliable biological interpretation, and that evidence-grounded orchestration is important for transparent and source-traceable transcriptomic reasoning.

q-bio.QM↗

arXiv2026

UAT-LITE: Inference-Time Uncertainty-Aware Attention for Pretrained Transformers

Neural NLP models are often miscalibrated and overconfident, assigning high confidence to incorrect predictions and failing to express uncertainty during internal evidence aggregation. This undermines selective prediction and high-stakes deployment. Post-hoc calibration methods adjust output probabilities but leave internal computation unchanged, while ensemble and Bayesian approaches improve uncertainty at substantial training or storage cost. We propose UAT-LITE, an inference-time framework that makes self-attention uncertainty-aware via Monte Carlo dropout in pretrained transformer classifiers. Unlike output-level calibration (e.g., TS), UAT-LITE injects epistemic uncertainty directly into attention, enabling uncertainty-aware routing during contextualization and token-level diagnostic signals beyond global logit rescaling. Token-level epistemic uncertainty is estimated from stochastic forward passes and used to modulate self-attention during contextualization, without modifying pretrained weights or training objectives. We additionally introduce a layer-wise variance decomposition to diagnose how predictive uncertainty accumulates across transformer depth. Across SQuAD 2.0 answerability, MNLI, and SST-2, UAT-LITE achieves an average relative ECE reduction of approximately 20% compared with a fine-tuned BERT-base baseline while preserving accuracy, and yields more informative uncertainty behavior for selective prediction under distribution shift.

cs.AI↗

arXiv2026

Can Transformer Memory Be Corrupted? Investigating Cache-Side Vulnerabilities in Large Language Models

Even when prompts and parameters are secured, transformer language models remain vulnerable because their key-value (KV) cache during inference constitutes an overlooked attack surface. This paper introduces Malicious Token Injection (MTI), a modular framework that systematically perturbs cached key vectors at selected layers and timesteps through controlled magnitude and frequency, using additive Gaussian noise, zeroing, and orthogonal rotations. A theoretical analysis quantifies how these perturbations propagate through attention, linking logit deviations to the Frobenius norm of corruption and softmax Lipschitz dynamics. Empirical results show that MTI significantly alters next-token distributions and downstream task performance across GPT-2 and LLaMA-2/7B, as well as destabilizes retrieval-augmented and agentic reasoning pipelines. These findings identify cache integrity as a critical yet underexplored vulnerability in current LLM deployments, positioning cache corruption as a reproducible and theoretically grounded threat model for future robustness and security research.

cs.CR↗

arXiv2025

Learning Robust Representations for Malicious Content Detection via Contrastive Sampling and Uncertainty Estimation

We propose the Uncertainty Contrastive Framework (UCF), a Positive-Unlabeled (PU) representation learning framework that integrates uncertainty-aware contrastive loss, adaptive temperature scaling, and a self-attention-guided LSTM encoder to improve classification under noisy and imbalanced conditions. UCF dynamically adjusts contrastive weighting based on sample confidence, stabilizes training using positive anchors, and adapts temperature parameters to batch-level variability. Applied to malicious content classification, UCF-generated embeddings enable multiple traditional classifiers to achieve more than 93.38% accuracy, precision above 0.93, and near-perfect recall, with minimal false negatives and competitive ROC-AUC scores. Visual analyses confirm clear separation between positive and unlabeled instances, highlighting the framework's ability to produce calibrated, discriminative embeddings. These results position UCF as a robust and scalable solution for PU learning in high-stakes domains such as cybersecurity and biomedical text mining.

cs.LG↗

arXiv2025

R-GAT: Cancer Document Classification Leveraging Graph-Based Residual Network for Scenarios with Limited Data

Accurate classification of cancer-related biomedical abstracts is critical for advancing cancer informatics and supporting decision-making in healthcare research. Yet progress in this domain is often constrained by limited availability of labeled corpora and the high computational demands of transformer-based approaches. To address these challenges, we propose a Residual Graph Attention Network (R-GAT) that integrates multi-head attention with residual connections to capture semantic and relational dependencies in biomedical texts. Evaluated on a curated dataset of 1,875 PubMed abstracts spanning thyroid, colon, lung, and generic cancer topics, R-GAT achieves stable and competitive performance, comparable to transformer-based models such as BioBERT and BioClinicalBERT and strong classical baselines like Logistic Regression, while requiring significantly fewer computational resources. Ablation studies confirm the importance of attention and residual connections in ensuring robustness under limited-data conditions. To support reproducibility and facilitate future research, we also release the curated dataset. Together, these contributions demonstrate the value of lightweight graph-based architectures as reliable and resource-efficient alternatives to computationally intensive transformers in biomedical NLP.

cs.AI↗

arXiv2025

Surformer v1: Transformer-Based Surface Classification Using Tactile and Vision Features

Surface material recognition is a key component in robotic perception and physical interaction, particularly when leveraging both tactile and visual sensory inputs. In this work, we propose Surformer v1, a transformer-based architecture designed for surface classification using structured tactile features and PCA-reduced visual embeddings extracted via ResNet-50. The model integrates modality-specific encoders with cross-modal attention layers, enabling rich interactions between vision and touch. Currently, state-of-the-art deep learning models for vision tasks have achieved remarkable performance. With this in mind, our first set of experiments focused exclusively on tactile-only surface classification. Using feature engineering, we trained and evaluated multiple machine learning models, assessing their accuracy and inference time. We then implemented an encoder-only Transformer model tailored for tactile features. This model not only achieved the highest accuracy but also demonstrated significantly faster inference time compared to other evaluated models, highlighting its potential for real-time applications. To extend this investigation, we introduced a multimodal fusion setup by combining vision and tactile inputs. We trained both Surformer v1 (using structured features) and Multimodal CNN (using raw images) to examine the impact of feature-based versus image-based multimodal learning on classification accuracy and computational efficiency. The results showed that Surformer v1 achieved 99.4% accuracy with an inference time of 0.77 ms, while the Multimodal CNN achieved slightly higher accuracy but required significantly more inference time. These findings suggest Surformer v1 offers a compelling balance between accuracy, efficiency, and computational cost for surface material recognition.

cs.CV↗

arXiv2025

AI Learning Algorithms: Deep Learning, Hybrid Models, and Large-Scale Model Integration

In this paper, we discuss learning algorithms and their importance in different types of applications which includes training to identify important patterns and features in a straightforward, easy-to-understand manner. We will review the main concepts of artificial intelligence (AI), machine learning (ML), deep learning (DL), and hybrid models. Some important subsets of Machine Learning algorithms such as supervised, unsupervised, and reinforcement learning are also discussed in this paper. These techniques can be used for some important tasks like prediction, classification, and segmentation. Convolutional Neural Networks (CNNs) are used for image and video processing and many more applications. We dive into the architecture of CNNs and how to integrate CNNs with ML algorithms to build hybrid models. This paper explores the vulnerability of learning algorithms to noise, leading to misclassification. We further discuss the integration of learning algorithms with Large Language Models (LLM) to generate coherent responses applicable to many domains such as healthcare, marketing, and finance by learning important patterns from large volumes of data. Furthermore, we discuss the next generation of learning algorithms and how we may have an unified Adaptive and Dynamic Network to perform important tasks. Overall, this article provides brief overview of learning algorithms, exploring their current state, applications and future direction.

cs.LG↗

arXiv2025

Edge-Based Learning for Improved Classification Under Adversarial Noise

Adversarial noise introduces small perturbations in images, misleading deep learning models into misclassification and significantly impacting recognition accuracy. In this study, we analyzed the effects of Fast Gradient Sign Method (FGSM) adversarial noise on image classification and investigated whether training on specific image features can improve robustness. We hypothesize that while adversarial noise perturbs various regions of an image, edges may remain relatively stable and provide essential structural information for classification. To test this, we conducted a series of experiments using brain tumor and COVID datasets. Initially, we trained the models on clean images and then introduced subtle adversarial perturbations, which caused deep learning models to significantly misclassify the images. Retraining on a combination of clean and noisy images led to improved performance. To evaluate the robustness of the edge features, we extracted edges from the original/clean images and trained the models exclusively on edge-based representations. When noise was introduced to the images, the edge-based models demonstrated greater resilience to adversarial attacks compared to those trained on the original or clean images. These results suggest that while adversarial noise is able to exploit complex non-edge regions significantly more than edges, the improvement in the accuracy after retraining is marginally more in the original data as compared to the edges. Thus, leveraging edge-based learning can improve the resilience of deep learning models against adversarial perturbations.

cs.CV↗

arXiv2024

From Questions to Insightful Answers: Building an Informed Chatbot for University Resources

This paper presents BARKPLUG V.2, a Large Language Model (LLM)-based chatbot system built using Retrieval Augmented Generation (RAG) pipelines to enhance the user experience and access to information within academic settings.The objective of BARKPLUG V.2 is to provide information to users about various campus resources, including academic departments, programs, campus facilities, and student resources at a university setting in an interactive fashion. Our system leverages university data as an external data corpus and ingests it into our RAG pipelines for domain-specific question-answering tasks. We evaluate the effectiveness of our system in generating accurate and pertinent responses for Mississippi State University, as a case study, using quantitative measures, employing frameworks such as Retrieval Augmented Generation Assessment(RAGAS). Furthermore, we evaluate the usability of this system via subjective satisfaction surveys using the System Usability Scale (SUS). Our system demonstrates impressive quantitative performance, with a mean RAGAS score of 0.96, and experience, as validated by usability assessments.

cs.ET↗

arXiv2023

Natural Language Processing in Electronic Health Records in Relation to Healthcare Decision-making: A Systematic Review

Background: Natural Language Processing (NLP) is widely used to extract clinical insights from Electronic Health Records (EHRs). However, the lack of annotated data, automated tools, and other challenges hinder the full utilisation of NLP for EHRs. Various Machine Learning (ML), Deep Learning (DL) and NLP techniques are studied and compared to understand the limitations and opportunities in this space comprehensively. Methodology: After screening 261 articles from 11 databases, we included 127 papers for full-text review covering seven categories of articles: 1) medical note classification, 2) clinical entity recognition, 3) text summarisation, 4) deep learning (DL) and transfer learning architecture, 5) information extraction, 6) Medical language translation and 7) other NLP applications. This study follows the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Result and Discussion: EHR was the most commonly used data type among the selected articles, and the datasets were primarily unstructured. Various ML and DL methods were used, with prediction or classification being the most common application of ML or DL. The most common use cases were: the International Classification of Diseases, Ninth Revision (ICD-9) classification, clinical note analysis, and named entity recognition (NER) for clinical descriptions and research on psychiatric disorders. Conclusion: We find that the adopted ML models were not adequately assessed. In addition, the data imbalance problem is quite important, yet we must find techniques to address this underlining problem. Future studies should address key limitations in studies, primarily identifying Lupus Nephritis, Suicide Attempts, perinatal self-harmed and ICD-9 classification.

cs.CL↗