arXiv:2604.12384v1 Announce Type: new Abstract: Safety alignment in Large Language Models (LLMs) remains highly fragile during fine-tuning, where even benign adaptation can degrade pre-trained refusal behaviors and enable harmful responses. Existing defenses typically constrain either weights or activations in isolation, without considering their coupled effects on safety. In this paper, we first theoretically demonstrate that […]
SOAR: Self-Correction for Optimal Alignment and Refinement in Diffusion Models
arXiv:2604.12617v1 Announce Type: cross Abstract: The post-training pipeline for diffusion models currently has two stages: supervised fine-tuning (SFT) on curated data and reinforcement learning (RL) with reward models. A fundamental gap separates them. SFT optimizes the denoiser only on ground-truth states sampled from the forward noising process; once inference deviates from these ideal states, subsequent […]
Enhancing Clustering: An Explainable Approach via Filtered Patterns
arXiv:2604.12460v1 Announce Type: new Abstract: Machine learning has become a central research area, with increasing attention devoted to explainable clustering, also known as conceptual clustering, which is a knowledge-driven unsupervised learning paradigm that partitions data into $theta$ disjoint clusters, where each cluster is described by an explicit symbolic representation, typically expressed as a closed pattern […]
A Two-Stage LLM Framework for Accessible and Verified XAI Explanations
arXiv:2604.12543v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly used to translate the technical outputs of eXplainable Artificial Intelligence (XAI) methods into accessible natural-language explanations. However, existing approaches often lack guarantees of accuracy, faithfulness, and completeness. At the same time, current efforts to evaluate such narratives remain largely subjective or confined to post-hoc […]
LLM-Guided Prompt Evolution for Password Guessing
arXiv:2604.12601v1 Announce Type: cross Abstract: Passwords still remain a dominant authentication method, yet their security is routinely subverted by predictable user choices and large-scale credential leaks. Automated password guessing is a key tool for stress-testing password policies and modeling attacker behavior. This paper applies LLM-driven evolutionary computation to automatically optimize prompts for the LLM password […]
DeepTest Tool Competition 2026: Benchmarking an LLM-Based Automotive Assistant
arXiv:2604.12615v1 Announce Type: new Abstract: This report summarizes the results of the first edition of the Large Language Model (LLM) Testing competition, held as part of the DeepTest workshop at ICSE 2026. Four tools competed in benchmarking an LLM-based car manual information retrieval application, with the objective of identifying user inputs for which the system […]
MorphDistill: Distilling Unified Morphological Knowledge from Pathology Foundation Models for Colorectal Cancer Survival Prediction
arXiv:2604.06390v2 Announce Type: replace-cross Abstract: Background: Colorectal cancer (CRC) remains a leading cause of cancer-related mortality worldwide. Accurate survival prediction is essential for treatment stratification, yet existing pathology foundation models often overlook organ-specific features critical for CRC prognostication. Methods: We propose MorphDistill, a two-stage framework that distills complementary knowledge from multiple pathology foundation models into […]
Broadening the Applicability of Conditional Syntax Splitting for Reasoning from Conditional Belief Bases
arXiv:2604.12660v1 Announce Type: new Abstract: In nonmonotonic reasoning from conditional belief bases, an inference operator satisfying syntax splitting postulates allows for taking only the relevant parts of a belief base into account, provided that the belief base splits into subbases based on disjoint signatures. Because such disjointness is rare in practice, safe conditional syntax splitting […]
KumoRFM-2: Scaling Foundation Models for Relational Learning
arXiv:2604.12596v1 Announce Type: cross Abstract: We introduce KumoRFM-2, the next iteration of a pre-trained foundation model for relational data. KumoRFM-2 supports in-context learning as well as fine-tuning and is applicable to a wide range of predictive tasks. In contrast to tabular foundation models, KumoRFM-2 natively operates on relational data, processing one or more connected tables […]
Differentiating Physical and Psychological Stress Using Wearable Physiological Signals and Salivary Cortisol
arXiv:2604.12671v1 Announce Type: new Abstract: Objective: This study aimed to assess how wearable physiological signals, alone and combined with salivary cortisol, distinguish physical and psychological stress and their recovery states. Methods: Six healthy adults completed three laboratory sessions on separate days: rest, physical stress (high-intensity cycling), or psychological stress (modified Trier Social Stress Test). Heart […]
DarwinNet: An Evolutionary Network Architecture for Agent-Driven Protocol Synthesis
arXiv:2604.01236v3 Announce Type: replace-cross Abstract: Traditional network architectures suffer from severe protocol ossification and structural fragility due to their reliance on static, human-defined rules that fail to adapt to the emergent edge cases and probabilistic reasoning of modern autonomous agents. To address these limitations, this paper proposes DarwinNet, a bio-inspired, self-evolving network architecture that transitions […]
When Does Data Augmentation Help? Evaluating LLM and Back-Translation Methods for Hausa and Fongbe NLP
arXiv:2604.12540v1 Announce Type: cross Abstract: Data scarcity limits NLP development for low-resource African languages. We evaluate two data augmentation methods — LLM-based generation (Gemini 2.5 Flash) and back-translation (NLLB-200) — for Hausa and Fongbe, two West African languages that differ substantially in LLM generation quality. We assess augmentation on named entity recognition (NER) and part-of-speech […]