Defines cost-aware RAG with evidence cost tiers and shows static selectors are brittle while agentic LLM-based selection is promising but model-dependent.
ICML '07: Proceedings of the 24th international conference on Machine learning , year =
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
Random undersampling reduces SPR measurements by a factor of 6 on a carbon fibre-aluminium composite using weighted random sampling on sparse signals.
A metric learning method is introduced to learn distance metrics that best capture conditional anomaly patterns in instance-based detection.
Instance-based conditional anomaly detection with optimized distance metrics detects unusual patient-management decisions in two real-world medical datasets.
citing papers explorer
-
When Knowledge Is Not Free: Cost-Aware Evidence Selection in Retrieval-Augmented Generation
Defines cost-aware RAG with evidence cost tiers and shows static selectors are brittle while agentic LLM-based selection is promising but model-dependent.
-
Thermal characterisation by Scanning Photothermal Radiometry using a random undersampled measurement scheme
Random undersampling reduces SPR measurements by a factor of 6 on a carbon fibre-aluminium composite using weighted random sampling on sparse signals.
-
Distance metric learning for conditional anomaly detection
A metric learning method is introduced to learn distance metrics that best capture conditional anomaly patterns in instance-based detection.
-
Conditional anomaly detection methods for patient-management alert systems
Instance-based conditional anomaly detection with optimized distance metrics detects unusual patient-management decisions in two real-world medical datasets.