Research Papers

Transformer-based large language models (LLMs) and multi-agent systems (MAS) are increasingly embedded across the software development lifecycle (SDLC), yet their fairness implications for developer-facing tools remain underexplored despite their growing role in shaping what code is written, reviewed, and released. We present a rapid review of recent work on fairness in MAS, emphasizing LLM-enabled settings and relevance to software engineering. Starting from an initial set of 350 papers, we screened and filtered the corpus for relevance, retaining 18 studies for final analysis. Across these 18 studies, fairness is framed as a combination of trustworthy AI principles, bias reduction across groups, and interactional dynamics in collectives, while evaluation spans accuracy metrics on bias benchmarks, demographic disparity measures, and emergent MAS-specific notions such as conformity and bias amplification. Reported harms include representational, quality-of-service, security and privacy, and governance failures, which we relate to SDLC stages where evidence is most and least developed. We identify three persistent gaps: (1) fragmented, rarely MAS-specific evaluation practices that limit comparability, (2) limited generalization due to simplified environments and narrow attribute coverage, and (3) scarce, weakly evaluated mitigation and governance mechanisms aligned to real software workflows. These findings suggest MAS fairness research is not yet ready to support deployable, fairness-assured software systems, motivating MAS-aware benchmarks, consistent protocols, and lifecycle-spanning governance.

The integration of large language models (LLMs) into peer review raises a concern beyond authorship and detection: the potential cascading automation of the entire editorial process. As reviews become partially or fully machine-generated, it becomes plausible that editorial decisions may also be delegated to algorithmic systems, leading to a fully automated evaluation pipeline. They risk reshaping the criteria by which scientific work is assessed. This paper argues that machine-driven assessment may systematically favor standardized, pattern-conforming research while penalizing unconventional and paradigm-shifting ideas that require contextual human judgment. We consider that this shift could lead to epistemic homogenization, where researchers are implicitly incentivized to optimize their work for algorithmic approval rather than genuine discovery. To address this risk, we introduce an explainable framework (RAG-XAI) for assessing review quality and detecting automated patterns using markers LLM extractor, aiming to preserve transparency, accountability and creativity in science. The proposed framework achieves near-perfect detection performance, with XGBoost, Random Forest and LightGBM reaching 99.61% accuracy, AUC-ROC above 0.999 and F1-scores of 0.9925 on the test set, while maintaining extremely low false positive rates (<0.23%) and false negative rates (~0.8%). In contrast, the logistic regression baseline performs substantially worse (89.97% accuracy, F1-score 0.8314). Feature importance and SHAP analyses identify absence of personal signals and repetition patterns as the dominant predictors. Additionally, the RAG component achieves 90.5% top-1 retrieval accuracy, with strong same-class clustering in the embedding space, further supporting the reliability of the framework's outputs.

Interpreting individual neurons in deep neural networks is a crucial step towards understanding their complex decision-making processes and ensuring AI safety. Despite recent progress in neuron labeling, existing methods often limit the search space to predefined concept vocabularies or produce overly specific descriptions that fail to capture higher-order, global concepts. We introduce LINE, a novel, training-free iterative approach tailored for open-vocabulary concept labeling in vision models. Operating in a strictly black-box setting, LINE leverages a large language model and a text-to-image generator to iteratively propose and refine concepts in a closed loop, guided by activation history. LINE achieves state-of-the-art performance across multiple model architectures, yielding AUC improvements of up to 0.11 on ImageNet and 0.05 on Places365, while discovering, on average, 27% of new concepts missed by predefined vocabularies. Beyond identifying the top concept, LINE provides a complete generation history, enabling polysemanticity evaluation and producing visual explanations that rival gradient-dependent activation maximization methods. The source code will be made available soon.

The polygenic risk scores (PRS) have emerged as an important methodology for quantifying genetic predisposition to complex traits and clinical disease. Significant progress has been made in applying PRS to conditions such as obesity, cancer, and type 2 diabetes (T2DM). Studies have demonstrated that PRS can effectively identify individuals at high risk, thereby enabling early screening, personalized treatment, and targeted interventions for diseases with a genetic predisposition. One current limitation of PRS, however, is the lack of interpretability tools. To address this problem for T2DM, researchers at the Graduate School of Data Science at the Seoul National University introduced eXplainable PRS (XPRS). This visualization tool decomposes PRSs into gene-level and single-nucleotide polymorphism (SNP) contribution scores via Shapley Additive Explanations (SHAP), providing granular insights into the specific genetic factors driving an individual's risk profile. We used a co-design approach to assess XPRS trustworthiness by considering legal, medical, ethical, and technical robustness during early design and potential clinical use. For that, we used Z-inspection, an ethically aligned Trustworthy AI co-design methodology, and piloted the Council of Europe's Human Rights, Democracy, and the Rule of Law Impact Assessment for AI Systems (HUDERIA) (Council of Europe (CAI) 2025). The findings of this use-case comprise a comprehensive set of ethical, legal, and technical lessons learned. These insights, identified by a multidisciplinary team of experts (ethics, legal, human rights, computer science, and medical), serve as a framework for designers to navigate future challenges with this and other AI systems. The findings also provide a useful reference for researchers developing explainability frameworks for PRS in diverse clinical contexts.

In this work we present a rigorous theoretical framework to a foundational problem of AI safety, namely adversarial robustness. In particular, we show that the adversarial robustness problem can be reduced to a lattice traversal problem. Each element of this lattice corresponds to an interval, i.e., an axis-aligned hyper-rectangle, containing an input point $\mathbf{x}$. Consider a multilayered perceptron classifier (MLP). An interval $I$ constitutes a sound certification if $\mathbf{x} \in I$ and $\mathbf{x}$ can be freely perturbed in $I$ without changing the MLP's prediction. Complementarily, an interval $I$ constitutes a complete certification if $\mathbf{x} \in I$ and when $\mathbf{x}$ moves outside of $I$ the MLP's prediction is guaranteed to change. While the sound certification problem corresponds to the well-studied adversarial robustness, complete certifications have not been examined in the literature. We develop lattice traversal operators, which we apply in a refine & verify iterative scheme. Using formal MLP verifiers, sound maximality and complete minimality are guaranteed. Moreover, we examine objective optimization problems. There we discover some interesting asymmetries. For complete certifications, the minimum solution is obtained in polynomial oracle calls. This does not hold for sound certifications, where we prove strong intractability results. Additionally, we examine optimization problems in symmetric intervals (i.e., $\ell_\infty$-spheres), where we provide logarithmic algorithms. Finally, we present an empirical evaluation, using the novel ParallelepipedoNN system.

Military human robot interaction (MHRI) presents a novel opportunity to blend the capabilities of autonomous and Artificial Intelligence (AI)-enabled systems with the skills and expertise of humans. The concept promises military advantages and greater operational effectiveness and efficiencies. However, the associated human-AI dynamics create challenges when attempting to design, implement, and operationalise the increasingly symbiotic relationship between humans and machines. Meaningful human control (MHC) is a popularised conceptualisation of what is deemed a responsible interaction among human and artificial agents; however, this notion falls short in military contexts and hinders the realisation of military advantages that could be achieved by advancing the adoption of responsible AI. This paper presents meaningful human command (MHC1) as a more operationally effective concept for advanced military command and control systems that embed AI-enabled autonomous systems. We introduce, explore, and unpack meaningful human command in the context of military human-robot interaction, presenting a vignette that offers a technologically feasible concept of an AI-enabled system within military operations. The vignette is used to guide, contextualise, and add realism to the narrative describing the concept and highlights associated MHRI challenges.

Although visual foundation models like DINOv2 provide state-of-the-art performance as feature extractors, their complex, high-dimensional representations create substantial hurdles for interpretability. This work proposes DINO-QPM, which converts these powerful but entangled features into contrastive, class-independent representations that are interpretable by humans. DINO-QPM is a lightweight interpretability adapter that pursues globally interpretable image classification, adapting the Quadratic Programming Enhanced Model (QPM) to operate on strictly frozen DINO backbones. While classification with visual foundation models typically relies on the \texttt{CLS} token, we deliberately diverge from this standard. By leveraging average-pooling, we directly connect the patch embeddings to the model's features and therefore enable spatial localisation of DINO-QPM's globally interpretable features within the input space. Furthermore, we apply a sparsity loss to minimise spatial scatter and background noise, ensuring that explanations are grounded in relevant object parts. With DINO-QPM we make the level of interpretability of QPM available as an adapter while exceeding the accuracy of DINOv2 linear probe. Evaluated through an introduced Plausibility metric and other interpretability metrics, extensive experiments demonstrate that DINO-QPM is superior to other applicable methods for frozen visual foundation models in both classification accuracy and explanation quality.

No feature ranking can be simultaneously faithful, stable, and complete when features are collinear. For collinear pairs, ranking reduces to a coin flip. We prove this impossibility, quantify it for four model classes, resolve it via ensemble averaging (DASH), and machine-verify it with 305 Lean 4 theorems. We characterize the complete attribution design space: exactly two families of methods exist -- faithful-complete methods (unstable, with rankings that flip up to 50% of the time) and ensemble methods like DASH (stable, reporting ties for symmetric features) -- and no method lies outside this dichotomy. The impossibility is quantitative: the attribution ratio diverges as 1/(1-rho^2) for gradient boosting, is infinite for Lasso, and converges for random forests. DASH (Diversified Aggregation of SHAP) is provably Pareto-optimal among unbiased aggregations, achieving the Cramer-Rao variance bound with a tight ensemble size formula. In a survey of 77 public datasets, 68% exhibit attribution instability. Switching to conditional SHAP does not escape the impossibility when features have equal causal effects. The framework includes practical diagnostics -- a Z-test workflow and single-model screening tool -- and has direct consequences for fairness auditing: SHAP-based proxy discrimination audits are provably unreliable under collinearity. The design space theorem, diagnostics, and impossibility are mechanically verified in Lean 4 (305 theorems from 16 axioms, 0 sorry) -- to our knowledge, the first formally verified impossibility in explainable AI.

Modern Transformer-based language models achieve strong performance in natural language processing tasks, yet their latent semantic spaces remain largely uninterpretable black boxes. This paper introduces LAG-XAI (Lie Affine Geometry for Explainable AI), a novel geometric framework that models paraphrasing not as discrete word substitutions, but as a structured affine transformation within the embedding space. By conceptualizing paraphrasing as a continuous geometric flow on a semantic manifold, we propose a computationally efficient mean-field approximation, inspired by local Lie group actions. This allows us to decompose paraphrase transitions into geometrically interpretable components: rotation, deformation, and translation. Experiments on the noisy PIT-2015 Twitter corpus, encoded with Sentence-BERT, reveal a "linear transparency" phenomenon. The proposed affine operator achieves an AUC of 0.7713. By normalizing against random chance (AUC 0.5), the model captures approximately 80% of the non-linear baseline's effective classification capacity (AUC 0.8405), offering explicit parametric interpretability in exchange for a marginal drop in absolute accuracy. The model identifies fundamental geometric invariants, including a stable matrix reconfiguration angle (~27.84°) and near-zero deformation, indicating local isometry. Cross-domain generalization is confirmed via direct cross-corpus validation on an independent TURL dataset. Furthermore, the practical utility of LAG-XAI is demonstrated in LLM hallucination detection: using a "cheap geometric check," the model automatically detected 95.3% of factual distortions on the HaluEval dataset by registering deviations beyond the permissible semantic corridor. This approach provides a mathematically grounded, resource-efficient path toward the mechanistic interpretability of Transformers.

Large language models (LLMs) frequently encode factual and reasoning knowledge in their internal representations that is not faithfully reflected in their surface-level outputs -- a phenomenon known as \emph{latent knowledge}. Existing approaches to eliciting latent knowledge, such as Contrastive Consistency Search (CCS), rely on contrastive activation patterns and struggle with complex multi-step reasoning tasks, while mechanistic interpretability tools have primarily been used to \emph{understand} model behavior rather than to \emph{extract} hidden knowledge. We present \textbf{MechELK}, a unified three-stage framework that bridges mechanistic interpretability and latent knowledge elicitation. MechELK operates through: (1) \textbf{Locate} -- using Sparse Autoencoder (SAE) feature analysis and activation patching to identify knowledge-bearing representations; (2) \textbf{Verify} -- employing causal probing to distinguish genuine latent knowledge from spurious correlations; and (3) \textbf{Elicit} -- applying representation engineering to surface hidden knowledge without modifying model weights. Evaluated on TruthfulQA, a curated Deceptive Alignment benchmark, and the Quirky LM dataset, MechELK achieves an average elicitation accuracy of 84.7\%, outperforming CCS by 6.2\% and direct linear probing by 9.1\%. Crucially, MechELK successfully identifies latent knowledge in 78.3\% of cases where the model's surface output is incorrect or evasive, demonstrating its utility for AI safety applications including deceptive alignment detection.

Empirical Characterization of Rationale Stability Under Controlled Perturbations for Explainable Pattern Recognition

Abu Noman Md Sakib, Zhensen Wang, Merjulah Roby +1

Reliable pattern recognition systems should exhibit consistent behavior across similar inputs, and their explanations should remain stable. However, most Explainable AI evaluations remain instance centric and do not explicitly quantify whether attribution patterns are consistent across samples that share the same class or represent small variations of the same input. In this work, we propose a novel metric aimed at assessing the consistency of model explanations, ensuring that models consistently reflect the intended objectives and consistency under label-preserving perturbations. We implement this metric using a pre-trained BERT model on the SST-2 sentiment analysis dataset, with additional robustness tests on RoBERTa, DistilBERT, and IMDB, applying SHAP to compute feature importance for various test samples. The proposed metric quantifies the cosine similarity of SHAP values for inputs with the same label, aiming to detect inconsistent behaviors, such as biased reliance on certain features or failure to maintain consistent reasoning for similar predictions. Through a series of experiments, we evaluate the ability of this metric to identify misaligned predictions and inconsistencies in model explanations. These experiments are compared against standard fidelity metrics to assess whether the new metric can effectively identify when a model's behavior deviates from its intended objectives. The proposed framework provides a deeper understanding of model behavior by enabling more robust verification of rationale stability, which is critical for building trustworthy AI systems. By quantifying whether models rely on consistent attribution patterns for similar inputs, the proposed approach supports more robust evaluation of model behavior in practical pattern recognition pipelines. Our code is publicly available at https://github.com/anmspro/ESS-XAI-Stability.

Chain-of-Thought (CoT) prompting has been used to enhance the reasoning capability of LLMs. However, its reliability in security-sensitive analytical tasks remains insufficiently examined, particularly under structured human evaluation. Alternative approaches, such as model scaling and fine-tuning can be used to help improve performance. These methods are also often costly, computationally intensive, or difficult to audit. In contrast, prompt engineering provides a lightweight, transparent, and controllable mechanism for guiding LLM reasoning. This study proposes a structured prompt engineering framework designed to strengthen CoT reasoning integrity while improving security threat and attack detection reliability in local LLM deployments. The framework includes 16 factors grouped into four core dimensions: (1) Context and Scope Control, (2) Evidence Grounding and Traceability, (3) Reasoning Structure and Cognitive Control, and (4) Security-Specific Analytical Constraints. Rather than optimizing the wording of the prompt heuristically, the framework introduces explicit reasoning controls to mitigate hallucination and prevent reasoning drift, as well as strengthening interpretability in security-sensitive contexts. Using DDoS attack detection in SDN traffic as a case study, multiple model families were evaluated under structured and unstructured prompting conditions. Pareto frontier analysis and ablation experiments demonstrate consistent reasoning improvements (up to 40% in smaller models) and stable accuracy gains across scales. Human evaluation with strong inter-rater agreement (Cohen's k > 0.80) confirms robustness. The results establish structured prompting as an effective and practical approach for reliable and explainable AI-driven cybersecurity analysis.