{"total":13,"rows":[{"id":"2110.07178","title":"Symbolic Knowledge Distillation: from General Language Models to Commonsense Models","created":"2021-10-14","cited_by_count":270,"area":"distill"},{"id":"2311.07052","title":"Towards the Law of Capacity Gap in Distilling Language Models","created":"2023-11-13","cited_by_count":44,"area":"distill"},{"id":"2403.00932","title":"Differentially Private Knowledge Distillation via Synthetic Text Generation","created":"2024-03-01","cited_by_count":18,"area":"distill"},{"id":"2505.12781","title":"A Token is Worth over 1,000 Tokens: Efficient Knowledge Distillation through Low-Rank Clone","created":"2025-05-19","cited_by_count":15,"area":"distill"},{"id":"2502.10914","title":"LLM-driven Knowledge Distillation for Dynamic Text-Attributed Graphs","created":"2025-02-15","cited_by_count":8,"area":"distill"},{"id":"2109.07049","title":"Self-Training with Differentiable Teacher","created":"2021-09-15","cited_by_count":7,"area":"distill"},{"id":"2312.13556","title":"Multi-Level Knowledge Distillation for Speech Emotion Recognition in Noisy Conditions","created":"2023-12-21","cited_by_count":4,"area":"distill"},{"id":"2505.07105","title":"Knowledge Distillation for Enhancing Walmart E-commerce Search Relevance Using Large Language Models","created":"2025-05-11","cited_by_count":4,"area":"distill"},{"id":"2405.08019","title":"AdaKD: Dynamic Knowledge Distillation of ASR models using Adaptive Loss Weighting","created":"2024-05-11","cited_by_count":3,"area":"distill"},{"id":"2205.12428","title":"Do we need Label Regularization to Fine-tune Pre-trained Language Models?","created":"2022-05-25","cited_by_count":2,"area":"distill"},{"id":"2509.15608","title":"Enhancing WSI-Based Survival Analysis with Report-Auxiliary Self-Distillation","created":"2025-09-19","cited_by_count":1,"area":"distill"},{"id":"2312.04193","title":"Language Model Knowledge Distillation for Efficient Question Answering in Spanish","created":"2023-12-07","cited_by_count":0,"area":"distill"},{"id":"2610.10854","title":"KDFP: A first-principles approach to knowledge distillation in large language models","created":"2026-10-07","cited_by_count":0,"area":"distill"}],"next_cursor":null}