arXiv AI October 28, 2026 By Ngoc Luyen Le, Marie-H\'el\`ene Abel, Bertrand Laforge

An Incremental Knowledge-Graph Learner Digital Twin for Evidence-Grounded Early Warning

The paper presents an incremental Learner Digital Twin that uses a lightweight knowledge graph to provide evidence‑grounded early warning in learning analytics. The twin is updated at temporal checkpoints by replaying learning traces and assessment records, enabling both feature extraction and explanation grounding. Evaluated on a public benchmark, the graph‑mediated approach preserves predictive performance while generating alerts that link risk decisions to specific evidence items and raw records.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

benchmarks

arXiv AI

Aug 26

Provenance Guided Incremental Learning Under Evolving Concept Definitions

The paper introduces a provenance-guided incremental learning framework that handles rule-induced concept shift, where target definitions are explicitly revised and previously stored instances receive new semantic labels. By compiling concept changes into structured rule deltas, tracing affected records through historical provenance, and selectively re-evaluating only a localized candidate region, the method automatically relabels executable revisions, manages ambiguous cases with selective supervision, and repairs predictors incrementally. Evaluation on the RuleShift-Bench benchmark—covering financial, demographic, cybersecurity, and graph-structured data—shows 92.3% accuracy and 90.2% Macro‑F1, reprocessing only 14.7% of the historical collection and achieving an average update latency of 179 s versus 993 s for full relabeling and retraining.

By Ismail Lamaakal

benchmarks

arXiv Machine Learning

Oct 7

To Learn is to Wander: Learning Across Graphs and Tasks with Random Walks

arXiv:2610.06694v2 Announce Type: replace Abstract: Graph foundation models aim to transfer across graphs, feature spaces, relational schemas, and prediction tasks, yet existing approaches typically...

By Louis Tichelman, Xingyue Huang, Jinwoo Kim, \.Ismail \.Ilkan Ceylan

benchmarks

arXiv Computer Vision

Sep 1

Knowing Beyond the Known: Reinforced Knowledge Specification for Multi-Label Class-Incremental Learning

arXiv:2608.30316v1 Announce Type: new Abstract: Existing class-incremental learning methods struggle in multi-label scenarios (MLCIL) due to the inherent contradiction of learning objectives arising...

By Aoting Zhang, Dongbao Yang, Chang Liu, Xiaopeng Hong, Can Ma, Yu Zhou

rag benchmarks

arXiv AI

Jul 22

Trajectory-Aware Clinical Risk Prediction via Severity-Grounded Knowledge Graphs and Retrieval-Augmented Generation

arXiv:2607. 18270v1 Announce Type: new Abstract: While Electronic Health Records (EHRs) offer a wealth of clinical data, effectively augmenting a patient's records with heterogeneous external knowledge to predict the patient's clinical risk remains a significant challenge.

By Kyunghoon Jeon, Youmin Ko, Woohwan Jung, Hyunjoon Kim

rag efficiency benchmarks

arXiv AI

Jul 22

LLM-Grounded Explainable AI for Supply Chain Risk Early Warning via Temporal Graph Attention Networks

arXiv:2603. 04818v3 Announce Type: replace Abstract: Disruptions at critical logistics nodes pose severe risks to global supply chains, yet existing risk prediction systems typically prioritize forecasting accuracy without providing operationally interpretable early warnings.

By Zhiming Xue, Yujue Wang, Menghao Huo

llms

arXiv AI

Jul 23

Stateful Guardrails for Multi-Turn LLM Systems: A Conversational Risk Accumulation Framework

arXiv:2607. 19361v1 Announce Type: cross Abstract: Most safety guardrails for large language models (LLMs) evaluate each prompt-response pair in isolation, which misses failures that arise only over a dialogue as benign turns compose into harm.

By Sanjay Mishra, Divya Chukkapalli, Ganesh R. Naik

llms benchmarks safety

One email a morning, machine-written

Related stories

Provenance Guided Incremental Learning Under Evolving Concept Definitions

To Learn is to Wander: Learning Across Graphs and Tasks with Random Walks

Knowing Beyond the Known: Reinforced Knowledge Specification for Multi-Label Class-Incremental Learning

Trajectory-Aware Clinical Risk Prediction via Severity-Grounded Knowledge Graphs and Retrieval-Augmented Generation

LLM-Grounded Explainable AI for Supply Chain Risk Early Warning via Temporal Graph Attention Networks

Stateful Guardrails for Multi-Turn LLM Systems: A Conversational Risk Accumulation Framework