paper
Context-Aware Distillation and Ablation for Text2DSL
paperactiveprovisional
context-aware-distillation-and-ablation-for-text2dsl-b953c9b8·1 events·first seen 6d agoAliases: Context-Aware Distillation and Ablation for Text2DSL
Co-occurring entities
More like this (12)
In-context Vector Distillationon-policy distillationModel DistillationOn-Policy Co-DistillationLearning from the Self-future: On-policy Self-distillation for dLLMsDense Supervision, Sparse Updates: On the Sparsity and Geometry of On-Policy DistillationOn-Policy Distillation (OPD)DirectAudioEdit: Inversion-Free Text-Guided Audio Editing via Diffusion Prediction ContrastGeneralized DistillationBeyond Fully Random Masking: Attention-Guided Denoising and Optimization for Diffusion Language ModelsDiffusion Language ModelsSelective Proxy Distillation
Recent events (1)
Context-aware distillation and ablation study for Text2DSL Polkit rule generation
Researchers extend a Text2DSL system for generating Polkit domain-specific language rules from natural language, replacing prompt-only synthetic data generation with context-aware distillation using DeepSeek-V4-Flash as a teacher model operating under structured context (BNF grammar, API spec, closed vocabulary). The approach scales a verified corpus from 4,204 to 10,073 NL-to-Polkit-rule pairs at near-perfect validity rates. A factorial ablation across eight context conditions on GigaChat-10B-A1.8B finds that structured context is load-bearing rather than cosmetic, with vocabulary contributing the largest semantic-quality gains via Shapley decomposition.