SieveFL combines vector retrieval and JaCoCo runtime pruning to cut LLM token use by 49% while achieving 41.8% Top-1 accuracy on 395 Defects4J bugs, outperforming AgentFL.
Confident learning: Estimating uncertainty in dataset labels
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
SLA detects noisy labels task-agnostically by standardizing and aggregating validation losses across repeated cross-validation folds, generalizing hard-counting into a continuous estimator that outperforms baselines on fundus data.
citing papers explorer
-
SieveFL: Hierarchical Runtime-Aware Pruning for Scalable LLM-Based Fault Localization
SieveFL combines vector retrieval and JaCoCo runtime pruning to cut LLM token use by 49% while achieving 41.8% Top-1 accuracy on 395 Defects4J bugs, outperforming AgentFL.
-
Task-Agnostic Noisy Label Detection via Standardized Loss Aggregation
SLA detects noisy labels task-agnostically by standardizing and aggregating validation losses across repeated cross-validation folds, generalizing hard-counting into a continuous estimator that outperforms baselines on fundus data.