Find a story
Search Spins
Search titles, summaries, and missing voices across published articles — press releases, announcements, and media coverage.
8 results for “domain knowledge”
ISEE: Interactive Semantic Enrichment for Database Fields
ISEE is a new interactive system that improves LLM agent performance on data tasks by collaboratively enriching ambiguous database field descriptions with user-provided domain knowledge.
Aug 5, 2026
DKCD: Domain Knowledge-Enhanced Causal Discovery from Unstructured Data
A new research framework called DKCD improves causal discovery from unstructured data in high-expertise domains by integrating domain knowledge into LLM-based reasoning, addressing latent factor identification and annotation reliability.
Jul 13, 2026
Towards Detecting Inconsistencies in End-to-end Generated TODs
Researchers propose a constraint satisfaction problem (CSP)-based method to automatically detect hallucinations and inconsistencies in task-oriented dialogues generated by LLMs, addressing a known reliability gap in end-to-end conversational AI systems.
Jul 13, 2026
Ceci n'est pas une pipe: AI systems as semantic abstractions
A new arXiv preprint introduces a semantic framework to rigorously distinguish between AI-generated outputs and factual reality, defining failure modes like extrapolation and unsupported assertion by grounding claims in domain knowledge, reference sources, and system capabilities.
Jul 13, 2026
KARMA: Knowledge graph-based Automated Reasoning Materialization and Alignment
KARMA is a new contrastive synthesis method that uses knowledge graphs to generate slot-aligned candidates and applies slot-level supervision to improve preference learning in LLMs.
Jul 8, 2026
Conditional Diffusion Guided Knowledge Transfer for Multi-Domain Knowledge Graph Completion
A new AI research paper proposes DMKGC, a diffusion-model-based framework for multi-domain knowledge graph completion that improves prediction accuracy by 4.3% MRR over prior methods while preserving domain-specific entity information.
Jul 8, 2026
Domain Knowledge Based Temporal-Spatial Graph Convolution Network for ECG Recognition
A new graph convolutional neural network architecture incorporating domain-specific ECG landmarks and temporal-spatial graph structures achieves 88.1% average F1 score on a nine-class Chinese ECG dataset, improving rare-class detection by embedding clinical knowledge into model design.
Published Jul 3, 2026 · Analyzed Jul 6, 2026
PACE: A Neuro-Symbolic Framework for Plausible and Actionable Counterfactual Explanations
PACE is a new neuro-symbolic framework that integrates neural prediction with symbolic reasoning to generate counterfactual explanations constrained by real-world domain feasibility — addressing a known weakness in explainable AI where counterfactuals are technically valid but practically implausible.
Published Jul 3, 2026 · Analyzed Jul 6, 2026