arXiv:2602.06841v3 Announce Type: replace Abstract: Over the last decade, explainable AI has primarily focused on interpreting individual model predictions, producing post-hoc explanations that relate inputs to outputs under a fixed decision structure. Recent advances in large language models (LLMs) have enabled agentic AI systems whose behaviour unfolds over multi-step trajectories. In these settings, success and […]
SpecFuse: Ensembling Large Language Models via Next-Segment Prediction
arXiv:2412.07380v3 Announce Type: replace-cross Abstract: Ensembles of generative large language models (LLMs) are a promising way to compensate for individual model limitations, integrating the strengths of different LLMs. Existing LLM ensemble methods, however, face limitations such as first-token delay and challenges in long-range semantic collaboration between models, Moreover, they typically assume equal voting weights for […]
CLoPA: Continual Low Parameter Adaptation of Interactive Segmentation for Medical Image Annotation
arXiv:2603.06426v1 Announce Type: cross Abstract: Interactive segmentation enables clinicians to guide annotation, but existing zero-shot models like nnInteractive fail to consistently reach expert-level performance across diverse medical imaging tasks. Because annotation campaigns produce a growing stream of task-specific labelled data, online adaptation of the segmentation model is a natural complement to zero-shot inference. We propose […]
Mean-based incomplete pairwise comparisons method with the reference values
arXiv:2207.10783v2 Announce Type: replace Abstract: In this article, we propose two quantitative methods for calculating weight vectors for incomplete pairwise comparison matrices using reference values. Both procedures are extensions of arithmetic and geometric heuristic estimation (HRE) methods. The proposed solutions allow flexible selection of the number of reference alternatives and the range of comparisons, from […]
LLMTM: Benchmarking and Optimizing LLMs for Temporal Motif Analysis in Dynamic Graphs
arXiv:2512.22266v2 Announce Type: replace-cross Abstract: The widespread application of Large Language Models (LLMs) has motivated a growing interest in their capacity for processing dynamic graphs. Temporal motifs, as an elementary unit and important local property of dynamic graphs which can directly reflect anomalies and unique phenomena, are essential for understanding their evolutionary dynamics and structural […]
An Adaptive Model Selection Framework for Demand Forecasting under Horizon-Induced Degradation to Support Business Strategy and Operations
arXiv:2602.13939v2 Announce Type: replace-cross Abstract: Business environments characterized by structural demand intermittency, high variability, and multi-step planning horizons require robust and reproducible model selection mechanisms. Empirical evidence shows that no forecasting model is universally dominant and that relative rankings vary across error metrics, demand regimes, and forecast horizons, generating ambiguity in multi-SKU decision contexts. This […]
Fine-Tuning and Evaluating Conversational AI for Agricultural Advisory
arXiv:2603.03294v2 Announce Type: replace-cross Abstract: Large Language Models show promise for agricultural advisory, yet vanilla models exhibit unsupported recommendations, generic advice lacking specific, actionable detail, and communication styles misaligned with smallholder farmer needs. In high stakes agricultural contexts, where recommendation accuracy has direct consequences for farmer outcomes, these limitations pose challenges for responsible deployment. We […]
Artificial Intelligence for Detecting Fetal Orofacial Clefts and Advancing Medical Education
arXiv:2603.06522v1 Announce Type: cross Abstract: Orofacial clefts are among the most common congenital craniofacial abnormalities, yet accurate prenatal detection remains challenging due to the scarcity of experienced specialists and the relative rarity of the condition. Early and reliable diagnosis is essential to enable timely clinical intervention and reduce associated morbidity. Here we show that an […]
Sysformer: Safeguarding Frozen Large Language Models with Adaptive System Prompts
arXiv:2506.15751v2 Announce Type: replace Abstract: As large language models (LLMs) are deployed in safety-critical settings, it is essential to ensure that their responses comply with safety standards. Prior research has revealed that LLMs often fail to grasp the notion of safe behaviors, resulting in either unjustified refusals to harmless prompts or the generation of harmful […]
SEA-TS: Self-Evolving Agent for Autonomous Code Generation of Time Series Forecasting Algorithms
arXiv:2603.04873v2 Announce Type: replace Abstract: Accurate time series forecasting underpins decision-making across domains, yet conventional ML development suffers from data scarcity in new deployments, poor adaptability under distribution shift, and diminishing returns from manual iteration. We propose Self-Evolving Agent for Time Series Algorithms (SEA-TS), a framework that autonomously generates, validates, and optimizes forecasting code via […]
From Tokenizer Bias to Backbone Capability: A Controlled Study of LLMs for Time Series Forecasting
arXiv:2504.08818v2 Announce Type: replace-cross Abstract: Using pre-trained large language models (LLMs) as a backbone for time series prediction has recently attracted growing research interest. Existing approaches typically split time series into patches, map them to the token space of LLMs via a Tokenizer, process the tokens through a frozen or fine-tuned LLM backbone, and then […]
MAP: Mitigating Hallucinations in Large Vision-Language Models with Map-Level Attention Processing
arXiv:2508.01653v2 Announce Type: replace-cross Abstract: Large Vision-Language Models (LVLMs) have achieved impressive performance in multimodal tasks, but they still suffer from hallucinations, i.e., generating content that is grammatically accurate but inconsistent with visual inputs. In this work, we introduce a novel map-level perspective to mitigate hallucinations in LVLMs, interpreting the hidden states of the model […]