Legal compliance in AI-driven data transfer planning is becoming increasingly critical under stringent privacy regulations such as the Japanese Act on the Protection of Personal Information (APPI). We propose a multi-agent legal verifier that decomposes compliance checking into specialized agents for statutory interpretation, business context evaluation, and risk assessment, coordinated through a structured synthesis protocol. Evaluated on a stratified dataset of 200 Amended APPI Article 16 cases with clearly defined ground truth labels and multiple performance metrics, the system achieves 72% accuracy, which is 21 percentage points higher than a single-agent baseline, including 90% accuracy on clear compliance cases (vs. 16% for the baseline) while maintaining perfect detection of clear violations. While challenges remain in ambiguous scenarios, these results show that domain specialization and coordinated reasoning can meaningfully improve legal AI performance, providing a scalable and regulation-aware framework for trustworthy and interpretable automated compliance verification.

Federated clustering addresses the critical challenge of extracting patterns from decentralized, unlabeled data. However, it is hampered by the flaw that current approaches are forced to accept a compromise between performance and privacy: \textit{transmitting embedding representations risks sensitive data leakage, while sharing only abstract cluster prototypes leads to diminished model accuracy}. To resolve this dilemma, we propose Structural Privacy-Preserving Federated Graph Clustering (SPP-FGC), a novel algorithm that innovatively leverages local structural graphs as the primary medium for privacy-preserving knowledge sharing, thus moving beyond the limitations of conventional techniques. Our framework operates on a clear client-server logic; on the client-side, each participant constructs a private structural graph that captures intrinsic data relationships, which the server then securely aggregates and aligns to form a comprehensive global graph from which a unified clustering structure is derived. The framework offers two distinct modes to suit different needs. SPP-FGC is designed as an efficient one-shot method that completes its task in a single communication round, ideal for rapid analysis. For more complex, unstructured data like images, SPP-FGC+ employs an iterative process where clients and the server collaboratively refine feature representations to achieve superior downstream performance. Extensive experiments demonstrate that our framework achieves state-of-the-art performance, improving clustering accuracy by up to 10\% (NMI) over federated baselines while maintaining provable privacy guarantees.

Modern text-to-speech (TTS) systems, particularly those built on Large Audio-Language Models (LALMs), generate high-fidelity speech that faithfully reproduces input text and mimics specified speaker identities. While prior misuse studies have focused on speaker impersonation, this work explores a distinct content-centric threat: exploiting TTS systems to produce speech containing harmful content. Realizing such threats poses two core challenges: (1) LALM safety alignment frequently rejects harmful prompts, yet existing jailbreak attacks are ill-suited for TTS because these systems are designed to faithfully vocalize any input text, and (2) real-world deployment pipelines often employ input/output filters that block harmful text and audio. We present HARMGEN, a suite of five attacks organized into two families that address these challenges. The first family employs semantic obfuscation techniques (Concat, Shuffle) that conceal harmful content within text. The second leverages audio-modality exploits (Read, Spell, Phoneme) that inject harmful content through auxiliary audio channels while maintaining benign textual prompts. Through evaluation across five commercial LALMs-based TTS systems and three datasets spanning two languages, we demonstrate that our attacks substantially reduce refusal rates and increase the toxicity of generated speech. We further assess both reactive countermeasures deployed by audio-streaming platforms and proactive defenses implemented by TTS providers. Our analysis reveals critical vulnerabilities: deepfake detectors underperform on high-fidelity audio; reactive moderation can be circumvented by adversarial perturbations; while proactive moderation detects 57-93% of attacks. Our work highlights a previously underexplored content-centric misuse vector for TTS and underscore the need for robust cross-modal safeguards throughout training and deployment.

Large language models (LLMs) have demonstrated capabilities across diverse domains, yet their performance on rare disease diagnosis from narrative medical cases remains underexplored. We introduce a novel dataset of 176 symptom-diagnosis pairs extracted from House M.D., a medical television series validated for teaching rare disease recognition in medical education. We evaluate four state-of-the-art LLMs such as GPT 4o mini, GPT 5 mini, Gemini 2.5 Flash, and Gemini 2.5 Pro on narrative-based diagnostic reasoning tasks. Results show significant variation in performance, ranging from 16.48% to 38.64% accuracy, with newer model generations demonstrating a 2.3 times improvement. While all models face substantial challenges with rare disease diagnosis, the observed improvement across architectures suggests promising directions for future development. Our educationally validated benchmark establishes baseline performance metrics for narrative medical reasoning and provides a publicly accessible evaluation framework for advancing AI-assisted diagnosis research.

The rapidly growing computation demands of deep neural networks (DNNs) have driven hardware vendors to integrate matrix multiplication accelerators (MMAs), such as NVIDIA Tensor Cores and AMD Matrix Cores, into modern GPUs. However, due to distinct and undocumented arithmetic specifications for floating-point matrix multiplication, some MMAs can lead to numerical imprecision and inconsistency that can compromise the stability and reproducibility of DNN training and inference. This paper presents MMA-Sim, the first bit-accurate reference model that reveals the detailed arithmetic behaviors of the MMAs from ten GPU architectures (eight from NVIDIA and two from AMD). By dissecting the MMAs using a combination of targeted and randomized tests, our methodology derives nine arithmetic algorithms to simulate the floating-point matrix multiplication of the MMAs. Large-scale validation confirms bitwise equivalence between MMA-Sim and the real hardware. Using MMA-Sim, we investigate arithmetic behaviors that affect DNN training stability, and identify undocumented behaviors that could lead to significant errors.

This paper explores the automatic classification of exam questions and learning outcomes according to Bloom's Taxonomy. A small dataset of 600 sentences labeled with six cognitive categories - Knowledge, Comprehension, Application, Analysis, Synthesis, and Evaluation - was processed using traditional machine learning (ML) models (Naive Bayes, Logistic Regression, Support Vector Machines), recurrent neural network architectures (LSTM, BiLSTM, GRU, BiGRU), transformer-based models (BERT and RoBERTa), and large language models (OpenAI, Gemini, Ollama, Anthropic). Each model was evaluated under different preprocessing and augmentation strategies (for example, synonym replacement, word embeddings, etc.). Among traditional ML approaches, Support Vector Machines (SVM) with data augmentation achieved the best overall performance, reaching 94 percent accuracy, recall, and F1 scores with minimal overfitting. In contrast, the RNN models and BERT suffered from severe overfitting, while RoBERTa initially overcame it but began to show signs as training progressed. Finally, zero-shot evaluations of large language models (LLMs) indicated that OpenAI and Gemini performed best among the tested LLMs, achieving approximately 0.72-0.73 accuracy and comparable F1 scores. These findings highlight the challenges of training complex deep models on limited data and underscore the value of careful data augmentation and simpler algorithms (such as augmented SVM) for Bloom's Taxonomy classification.

Multimodal emotion recognition plays a key role in many domains, including mental health monitoring, educational interaction, and human-computer interaction. However, existing methods often face three major challenges: unbalanced category distribution, the complexity of dynamic facial action unit time modeling, and the difficulty of feature fusion due to modal heterogeneity. With the explosive growth of multimodal data in social media scenarios, the need for building an efficient cross-modal fusion framework for emotion recognition is becoming increasingly urgent. To this end, this paper proposes Multimodal Cross-Attention Network and Contrastive Learning (MCN-CL) for mul-timodal emotion recognition. It uses a triple query mechanism and hard negative mining strategy to remove feature redundancy while preserving important emotional cues, effectively addressing the issues of modal heterogeneity and category imbalance. Experiment results on the IEMO-CAP and MELD datasets show that our proposed method outperforms state-of-the-art approaches, with Weighted F1 scores improving by 3.42% and 5.73%, respectively.

Progress in biomedical Named Entity Recognition (NER) and Entity Linking (EL) is currently hindered by a fragmented data landscape, a lack of resources for building explainable models, and the limitations of semantically-blind evaluation metrics. To address these challenges, we present MedPath, a large-scale and multi-domain biomedical EL dataset that builds upon nine existing expert-annotated EL datasets. In MedPath, all entities are 1) normalized using the latest version of the Unified Medical Language System (UMLS), 2) augmented with mappings to 62 other biomedical vocabularies and, crucially, 3) enriched with full ontological paths -- i.e., from general to specific -- in up to 11 biomedical vocabularies. MedPath directly enables new research frontiers in biomedical NLP, facilitating training and evaluation of semantic-rich and interpretable EL systems, and the development of the next generation of interoperable and explainable clinical NLP models.

Abstract--Negative bias refers to the tendency of large language models (LLMs) to excessively generate negative responses in binary decision tasks (e.g., yes-no question answering). Previous research has focused on detecting and addressing negative attention heads that induce negative bias. However, the underlying detailed factors influencing negative bias remain underexplored. In this paper, we demonstrate that LLMs exhibit format-level negative bias, meaning the prompt format more influences their responses than the semantics of the negative response. For the fine-grained study of the negative bias, we introduce a pipeline for constructing the evaluation set, which systematically categorizes the dataset into three subsets based on the model's parametric knowledge: correct, incorrect, and insufficient relevant knowledge. Through analysis of this evaluation set, we identify a shortcut behavior in which models tend to generate negative responses when they lack sufficient knowledge to answer a yes-no question, leading to negative bias. We further examine how negative bias changes under various prompting scenarios related to parametric knowledge. We observe that providing relevant context and offering an "I don't know" option generally reduces negative bias, whereas chain-of-thought prompting tends to amplify the bias. Finally, we demonstrate that the degree of negative bias can vary depending on the type of prompt, which influences the direction of the response. Our work reveals the various factors that influence negative bias, providing critical insights for mitigating it in LLMs. ECENT advances in the capabilities and emergent abilities of large language models (LLMs) have led to rapid improvements in the performance of a wide range of natural language processing (NLP) tasks [1]-[5]. Leveraging their ability to follow instructions, LLMs are able to perform complex, previously unseen tasks, enabling human-like interactions [6]-[9]. One critical issue is the hallucination problem, where the model generates content that contains misleading information, which does not correspond to the given context or real-world knowledge [11]. J. Song was with the Department of Electrical and Computer Engineering at Seoul National University, South Korea (coms1580@gmail.com).

Large Language Models (LLMs) have become ubiquitous in everyday life and are entering higher-stakes applications ranging from summarizing meeting transcripts to answering doctors' questions. As was the case with earlier predictive models, it is crucial that we develop tools for explaining the output of LLMs, be it a summary, list, response to a question, etc. With these needs in mind, we introduce In-Context Explainability 360 (ICX360), an open-source Python toolkit for explaining LLMs with a focus on the user-provided context (or prompts in general) that are fed to the LLMs. ICX360 contains implementations for three recent tools that explain LLMs using both black-box and white-box methods (via perturbations and gradients respectively).