{"total":27,"rows":[{"id":"2402.13116","title":"A Survey on Knowledge Distillation of Large Language Models","created":"2024-02-20","cited_by_count":284,"area":"distill"},{"id":"2407.01885","title":"Survey on Knowledge Distillation for Large Language Models: Methods, Evaluation, and Application","created":"2024-07-02","cited_by_count":56,"area":"distill"},{"id":"2109.08359","title":"Distilling Linguistic Context for Language Model Compression","created":"2021-09-17","cited_by_count":33,"area":"distill"},{"id":"2410.16215","title":"Pre-training Distillation for Large Language Models: A Design Space Exploration","created":"2024-10-21","cited_by_count":27,"area":"distill"},{"id":"2302.09632","title":"HomoDistil: Homotopic Task-Agnostic Distillation of Pre-trained Transformers","created":"2023-02-19","cited_by_count":25,"area":"distill"},{"id":"2109.10164","title":"RAIL-KD: RAndom Intermediate Layer Mapping for Knowledge Distillation","created":"2021-09-21","cited_by_count":19,"area":"distill"},{"id":"2206.01859","title":"Extreme Compression for Pre-trained Transformers Made Simple and Efficient","created":"2022-06-04","cited_by_count":19,"area":"distill"},{"id":"2405.17890","title":"SLMRec: Distilling Large Language Models into Small for Sequential Recommendation","created":"2024-05-28","cited_by_count":18,"area":"distill"},{"id":"2101.05938","title":"KDLSQ-BERT: A Quantized Bert Combining Knowledge Distillation with Learned Step Size Quantization","created":"2021-01-15","cited_by_count":15,"area":"distill"},{"id":"2108.08042","title":"Joint Multiple Intent Detection and Slot Filling via Self-distillation","created":"2021-08-18","cited_by_count":12,"area":"distill"},{"id":"2205.01915","title":"Generalized Knowledge Distillation via Relationship Matching","created":"2022-05-04","cited_by_count":12,"area":"distill"},{"id":"2101.08890","title":"Distilling Large Language Models into Tiny and Effective Students using pQRNN","created":"2021-01-21","cited_by_count":10,"area":"distill"},{"id":"2212.07634","title":"Gradient-based Intra-attention Pruning on Pre-trained Language Models","created":"2022-12-15","cited_by_count":9,"area":"distill"},{"id":"2205.07523","title":"Prompting to Distill: Boosting Data-Free Knowledge Distillation via Reinforced Prompt","created":"2022-05-16","cited_by_count":8,"area":"distill"},{"id":"2305.09098","title":"Weight-Inherited Distillation for Task-Agnostic BERT Compression","created":"2023-05-16","cited_by_count":8,"area":"distill"},{"id":"2104.11928","title":"Extract then Distill: Efficient and Effective Task-Agnostic BERT Distillation","created":"2021-04-24","cited_by_count":6,"area":"distill"},{"id":"2106.05691","title":"Marginal Utility Diminishes: Exploring the Minimum Knowledge for BERT Knowledge Distillation","created":"2021-06-10","cited_by_count":6,"area":"distill"},{"id":"2309.15494","title":"VideoAdviser: Video Knowledge Distillation for Multimodal Transfer Learning","created":"2023-09-27","cited_by_count":6,"area":"distill"},{"id":"2404.01353","title":"Efficiently Distilling LLMs for Edge Applications","created":"2024-04-01","cited_by_count":5,"area":"distill"},{"id":"2208.09684","title":"Combining Compressions for Multiplicative Size Scaling on Natural Language Tasks","created":"2022-08-20","cited_by_count":4,"area":"distill"},{"id":"2201.12507","title":"AutoDistil: Few-shot Task-agnostic Neural Architecture Search for Distilling Large Language Models","created":"2022-01-29","cited_by_count":3,"area":"distill"},{"id":"2311.01689","title":"Data-Free Distillation of Language Model by Text-to-Text Transfer","created":"2023-11-03","cited_by_count":1,"area":"distill"},{"id":"2310.02594","title":"I$^2$KD-SLU: An Intra-Inter Knowledge Distillation Framework for Zero-Shot Cross-Lingual Spoken Language Understanding","created":"2023-10-04","cited_by_count":0,"area":"distill"},{"id":"2310.13418","title":"GenDistiller: Distilling Pre-trained Language Models based on Generative Models","created":"2023-10-20","cited_by_count":0,"area":"distill"},{"id":"2505.16956","title":"On Multilingual Encoder Language Model Compression for Low-Resource Languages","created":"2025-05-22","cited_by_count":0,"area":"distill"},{"id":"2604.03110","title":"Multi-Aspect Knowledge Distillation for Language Model with Low-rank Factorization","created":"2026-04-03","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}