Retrieval pipelines, vector search, chunking and reranking: how models are grounded in a corpus instead of their weights.
arXiv:2609.15234v1 Announce Type: new Abstract: Recently, Large Language Models (LLMs) have gained significant attention due to their strong language understanding and generation capabilities, demons...
arXiv:2609.14451v1 Announce Type: cross Abstract: Modern semi-supervised learning (SSL) couples pseudo-label generation and classifier training, using the classifier's own confidence to select the ps...
The paper introduces a three‑layer diagnostic framework that separates errors in Graph‑RAG systems into reasoning loss, Knowledge Graph defects, and Cypher generation errors. Experiments on a spatio‑temporal ecological KG from southeastern Tibet show that data integrity issues, especially structural defects, are the main cause of performance drops, reducing accuracy from 0.93 to 0.39. The study also identifies a Parametric Knowledge Masking Effect where LLMs hide retrieval path failures, masking over 70 % of query generation errors and raising the risk of false negatives in automated monitoring.
The paper introduces AdaConRed, a label‑free post‑conformal decision rule that transforms ambiguous conformal prediction sets into single class assignments for medical image classification. It employs a five‑stage pipeline—vision‑language generative augmentation, a frozen DermFoundation encoder, a lightweight MLP classifier, an entropy‑modulated margin‑aware nonconformity score, and a reassignment step for transitional samples—to improve accuracy on OSCC and ISIC benchmarks. Results show notable gains in malignant class accuracy while maintaining overall performance.
arXiv:2609.15671v1 Announce Type: cross Abstract: Visual Question Answering (VQA) with Vision-Language Models (VLMs) is increasingly used in privacy-sensitive and bandwidth-constrained settings. Fede...
ProtoCAM is an explainable few‑shot learning framework for classifying breast lesions in ultrasound images. It combines mask‑guided feature encoding, prototypical metric learning, and gradient‑based visual explanations to leverage limited annotated data. Evaluated on the BUSI dataset, ProtoCAM achieved a macro F1‑score of 0.910 in a 3‑way 5‑shot setting, outperforming standard supervised CNNs, with ResNet18 reaching 91.65% under 15‑shot conditions.
arXiv:2609.13595v1 Announce Type: cross Abstract: Predicting potential dangers is core to safety. Forecasting the presence of other traffic agents is core to danger prediction. Occluded traffic agent...
arXiv:2609.14572v1 Announce Type: cross Abstract: Teaching abstract theoretical computer science (TCS) concepts such as algorithm analysis and complexity theory is challenging because students must h...
The paper evaluates seven open‑source large language models for retrieval‑augmented generation in the ESG reporting domain, using 498 real‑world ESG reports from EU‑listed companies and 100 synthetic QA pairs. Performance is measured with RAGAS metrics, showing strong retrieval scores but variable generation quality, especially in faithfulness and factual correctness. The results highlight significant differences across model architectures and underscore the need for domain‑specific fine‑tuning to improve factual accuracy.
arXiv:2512.20257v2 Announce Type: replace Abstract: With the rise of easily accessible generative tools for creating and manipulating multimedia content, the threat of realistic synthetic alterations...
arXiv:2609.14762v1 Announce Type: cross Abstract: Cloud-hosted large language models (LLMs) are increasingly used for root cause analysis (RCA) in AIOps pipelines, but they introduce data privacy ris...
arXiv:2609.15150v1 Announce Type: new Abstract: Unpaired cross-modal distillation transfers grade structure from histopathology into a micro-ultrasound (micro-US) encoder by aligning a pooled needle-...
The paper introduces DiCEf, a variant of the DiCE counterfactual example generator that incorporates expert knowledge expressed as a fuzzy linguistic vocabulary. By embedding continuous data into this linguistic domain, DiCEf personalises counterfactual explanations to be linguistically perceptible while maintaining minimal cost, sparsity, and diversity. Experimental results on a real‑world dataset demonstrate that this approach yields semantically meaningful counterfactuals for the explainee.
arXiv:2602.04192v3 Announce Type: replace Abstract: Learning the intrinsic dimensionality of subjective perceptual spaces such as taste, smell, or aesthetics from ordinal data is a challenging proble...
arXiv:2609.08797v2 Announce Type: replace-cross Abstract: The Potts model extends the Ising model to multinomial data. We introduce a Rater Ising-Potts model that uses agreement indicators between pa...
arXiv:2609.14485v1 Announce Type: new Abstract: Retrieval-Guided Fine-Tuning (RAG-FT) incorporates retrieved data directly into the training objective, but the statistical consequences of noisy retri...
arXiv:2609.14963v1 Announce Type: new Abstract: As large language models become capable translators of classical texts, a key challenge is deciding which outputs need expert review when no human refe...
arXiv:2609.14360v1 Announce Type: new Abstract: In practical molecular characterization, small-molecule structure identification benefits from complementary spectroscopic evidence, but missing, degra...
arXiv:2609.14449v1 Announce Type: new Abstract: Recent work has shown that a teacher model can transfer a bias to a student through a dataset from which every explicit reference to that bias has been...
The paper introduces a multimodal foundation model for lunar remote sensing, trained from scratch on SomBench—a dataset of nearly two million co‑registered tile bundles across 11 modalities at 1 m and 100 m resolutions. The model extends the TerraMind masked‑token architecture with lunar‑specific features such as explicit acquisition geometry and joint training of two spatial scales, and employs FlexiViT patch embeddings for adaptable patch sizes. Evaluation on crater detection, irregular mare patch segmentation, and polar ice prospectivity regression shows that the pretrained model matches or surpasses ImageNet‑pretrained baselines, with notable label efficiency and effective adaptation via LoRA.