{"total":76,"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":"2402.03898","title":"DistiLLM: Towards Streamlined Distillation for Large Language Models","created":"2024-02-06","cited_by_count":163,"area":"distill"},{"id":"2306.08543","title":"MiniLLM: On-Policy Distillation of Large Language Models","created":"2023-06-14","cited_by_count":139,"area":"distill"},{"id":"2402.13669","title":"Self-Distillation Bridges Distribution Gap in Language Model Fine-Tuning","created":"2024-02-21","cited_by_count":96,"area":"distill"},{"id":"2410.11325","title":"Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling","created":"2024-10-15","cited_by_count":90,"area":"distill"},{"id":"2511.10643","title":"Black-Box On-Policy Distillation of Large Language Models","created":"2025-11-13","cited_by_count":59,"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":"2402.11890","title":"Revisiting Knowledge Distillation for Autoregressive Language Models","created":"2024-02-19","cited_by_count":42,"area":"distill"},{"id":"2604.01193","title":"Embarrassingly Simple Self-Distillation Improves Code Generation","created":"2026-04-01","cited_by_count":40,"area":"distill"},{"id":"2604.17535","title":"OPSDL: On-Policy Self-Distillation for Long-Context Language Models","created":"2026-04-19","cited_by_count":30,"area":"distill"},{"id":"2504.14772","title":"Knowledge Distillation and Dataset Distillation of Large Language Models: Emerging Trends, Challenges, and Future Directions","created":"2025-04-20","cited_by_count":26,"area":"distill"},{"id":"2402.12842","title":"PromptKD: Distilling Student-Friendly Knowledge for Generative Language Models via Prompt Tuning","created":"2024-02-20","cited_by_count":25,"area":"distill"},{"id":"2406.17328","title":"Dual-Space Knowledge Distillation for Large Language Models","created":"2024-06-25","cited_by_count":25,"area":"distill"},{"id":"2609.04172","title":"Rethinking On-Policy Distillation of Large Language Models II: One Training Example","created":"2026-09-03","cited_by_count":24,"area":"distill"},{"id":"2505.04560","title":"ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via $\\alpha$-$\\beta$-Divergence","created":"2025-05-07","cited_by_count":23,"area":"distill"},{"id":"2410.18837","title":"High-dimensional Analysis of Knowledge Distillation: Weak-to-Strong Generalization and Scaling Laws","created":"2024-10-24","cited_by_count":22,"area":"distill"},{"id":"2308.06744","title":"Token-Scaled Logit Distillation for Ternary Weight Generative Language Models","created":"2023-08-13","cited_by_count":20,"area":"distill"},{"id":"2410.01524","title":"HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models","created":"2024-10-02","cited_by_count":19,"area":"distill"},{"id":"2410.04638","title":"Provable Weak-to-Strong Generalization via Benign Overfitting","created":"2024-10-06","cited_by_count":16,"area":"distill"},{"id":"2503.16870","title":"Sparse Logit Sampling: Accelerating Knowledge Distillation in LLMs","created":"2025-03-21","cited_by_count":16,"area":"distill"},{"id":"2510.11615","title":"LLM-Oriented Token-Adaptive Knowledge Distillation","created":"2025-10-13","cited_by_count":13,"area":"distill"},{"id":"2403.06414","title":"Evolving Knowledge Distillation with Large Language Models and Active Learning","created":"2024-03-11","cited_by_count":12,"area":"distill"},{"id":"2410.05725","title":"KnowledgeSG: Privacy-Preserving Synthetic Text Generation with Knowledge Distillation from Server","created":"2024-10-08","cited_by_count":11,"area":"distill"},{"id":"2408.10210","title":"A Survey on Symbolic Knowledge Distillation of Large Language Models","created":"2024-07-12","cited_by_count":9,"area":"distill"},{"id":"2410.19503","title":"SWITCH: Studying with Teacher for Knowledge Distillation of Large Language Models","created":"2024-10-25","cited_by_count":9,"area":"distill"},{"id":"2604.20244","title":"Hybrid Policy Distillation for LLMs","created":"2026-04-22","cited_by_count":9,"area":"distill"},{"id":"2305.04978","title":"NeuroComparatives: Neuro-Symbolic Distillation of Comparative Knowledge","created":"2023-05-08","cited_by_count":8,"area":"distill"},{"id":"2311.13621","title":"EA-KD: Entropy-based Adaptive Knowledge Distillation","created":"2023-11-22","cited_by_count":8,"area":"distill"},{"id":"2504.11426","title":"A Dual-Space Framework for General Knowledge Distillation of Large Language Models","created":"2025-04-15","cited_by_count":8,"area":"distill"},{"id":"2605.12741","title":"Learning with Rare Success but Rich Feedback via Reflection-Enhanced Self-Distillation","created":"2026-05-12","cited_by_count":8,"area":"distill"},{"id":"2310.18628","title":"Personalised Distillation: Empowering Open-Sourced LLMs with Adaptive Learning for Code Generation","created":"2023-10-28","cited_by_count":7,"area":"distill"},{"id":"2604.03873","title":"SODA: Semi On-Policy Black-Box Distillation for Large Language Models","created":"2026-04-04","cited_by_count":7,"area":"distill"},{"id":"2605.20643","title":"AVSD: Adaptive-View Self-Distillation by Balancing Consensus and Teacher-Specific Privileged Signals","created":"2026-05-20","cited_by_count":7,"area":"distill"},{"id":"2411.19638","title":"LLM Teacher-Student Framework for Text Classification With No Manually Annotated Data: A Case Study in IPTC News Topic Classification","created":"2024-11-29","cited_by_count":6,"area":"distill"},{"id":"2405.04781","title":"CourseGPT-zh: an Educational Large Language Model Based on Knowledge Distillation Incorporating Prompt Optimization","created":"2024-05-08","cited_by_count":5,"area":"distill"},{"id":"2602.21669","title":"DWA-KD: Dual-Space Weighting and Time-Warped Alignment for Cross-Tokenizer Knowledge Distillation","created":"2026-02-25","cited_by_count":5,"area":"distill"},{"id":"2604.00223","title":"Diversity-Aware Reverse Kullback-Leibler Divergence for Large Language Model Distillation","created":"2026-03-31","cited_by_count":5,"area":"distill"},{"id":"2406.02959","title":"Adversarial Moment-Matching Distillation of Large Language Models","created":"2024-06-05","cited_by_count":4,"area":"distill"},{"id":"2411.13045","title":"Explainable LLM-driven Multi-dimensional Distillation for E-Commerce Relevance Learning","created":"2024-11-20","cited_by_count":4,"area":"distill"},{"id":"2506.05695","title":"Being Strong Progressively! Enhancing Knowledge Distillation of Large Language Models through a Curriculum Learning Framework","created":"2025-06-06","cited_by_count":4,"area":"distill"},{"id":"2510.02302","title":"Knowledge Distillation Detection for Open-weights Models","created":"2025-10-02","cited_by_count":4,"area":"distill"},{"id":"2301.12609","title":"Knowledge Distillation $\\approx$ Label Smoothing: Fact or Fallacy?","created":"2023-01-30","cited_by_count":3,"area":"distill"},{"id":"2403.14171","title":"MMIDR: Teaching Large Language Model to Interpret Multimodal Misinformation via Knowledge Distillation","created":"2024-03-21","cited_by_count":3,"area":"distill"},{"id":"2406.19227","title":"Aligning Teacher with Student Preferences for Tailored Training Data Generation","created":"2024-06-27","cited_by_count":3,"area":"distill"},{"id":"2409.12512","title":"Exploring and Enhancing the Transfer of Distribution in Knowledge Distillation for Autoregressive Language Models","created":"2024-09-19","cited_by_count":3,"area":"distill"},{"id":"2503.14167","title":"Synthetic Clarification and Correction Dialogues about Data-Centric Tasks -- A Teacher-Student Approach","created":"2025-03-18","cited_by_count":3,"area":"distill"},{"id":"2508.07054","title":"Membership and Memorization in LLM Knowledge Distillation","created":"2025-08-09","cited_by_count":3,"area":"distill"},{"id":"2605.23857","title":"Strong Teacher Not Needed? On Distillation in LLM Pretraining","created":"2026-05-22","cited_by_count":3,"area":"distill"},{"id":"2407.10068","title":"Multi-Granularity Semantic Revision for Large Language Model Distillation","created":"2024-07-14","cited_by_count":2,"area":"distill"},{"id":"2510.15982","title":"AMiD: Knowledge Distillation for LLMs with $\\alpha$-mixture Assistant Distribution","created":"2025-10-13","cited_by_count":2,"area":"distill"},{"id":"2608.22788","title":"TailSieve: Partial-Rollout-Guided Tail Routing for LLM Rollouts","created":"2026-08-24","cited_by_count":2,"area":"distill"},{"id":"2410.00558","title":"AMR-Evol: Adaptive Modular Response Evolution Elicits Better Knowledge Distillation for Large Language Models in Code Generation","created":"2024-10-01","cited_by_count":1,"area":"distill"},{"id":"2507.10155","title":"What Should Feature Distillation Transfer in LLMs? A Task-Tangent Geometry View","created":"2025-07-14","cited_by_count":1,"area":"distill"},{"id":"2511.13767","title":"Dynamic Temperature Scheduler for Knowledge Distillation","created":"2025-11-14","cited_by_count":1,"area":"distill"},{"id":"2603.22056","title":"Dual-Space Knowledge Distillation with Key-Query Matching for Large Language Models with Vocabulary Mismatch","created":"2026-03-23","cited_by_count":1,"area":"distill"},{"id":"2606.00628","title":"Robust Reasoning via Dynamic Token Selection for Distribution-Aligned Self-Distillation","created":"2026-05-30","cited_by_count":1,"area":"distill"},{"id":"2608.08764","title":"Learning from Consensus and Disagreement: Unsupervised On-Policy Self-Distillation with Minority-Trajectory Contrast","created":"2026-08-09","cited_by_count":1,"area":"distill"},{"id":"2609.14193","title":"Data-Free On-Policy Distillation: How Far Can We Go Without External Data?","created":"2026-09-12","cited_by_count":1,"area":"distill"},{"id":"2503.16511","title":"Token-Level Uncertainty-Aware Objective for Language Model Post-Training","created":"2025-03-15","cited_by_count":0,"area":"distill"},{"id":"2509.25253","title":"Knowledge distillation through geometry-aware representational alignment","created":"2025-09-27","cited_by_count":0,"area":"distill"},{"id":"2510.24425","title":"Comprehensive and Efficient Distillation for Lightweight Sentiment Analysis Models","created":"2025-10-28","cited_by_count":0,"area":"distill"},{"id":"2601.16219","title":"Domain Specific Specialization in Low-Resource Settings: The Efficacy of Offline Response-Based Knowledge Distillation in Large Language Models","created":"2026-01-05","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":"2605.26246","title":"The Bridge-Garden Dilemma in LLM Distillation: Why Mixing Hard and Soft Labels Works","created":"2026-05-25","cited_by_count":0,"area":"distill"},{"id":"2606.01292","title":"What Makes a Strong Model? A Unified Spectral Analysis of Knowledge Transfer over High-dimensional Linear Regression","created":"2026-05-31","cited_by_count":0,"area":"distill"},{"id":"2606.29869","title":"ARKD: Adaptive Reinforcement Learning-Guided Bidirectional KL Divergence Distillation for Text Generation","created":"2026-06-29","cited_by_count":0,"area":"distill"},{"id":"2607.08161","title":"SQuaD-SQL: Efficient Text-to-SQL with Small Language Models via LLM-Guided Knowledge Distillation","created":"2026-07-09","cited_by_count":0,"area":"distill"},{"id":"2607.08776","title":"A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions","created":"2026-05-05","cited_by_count":0,"area":"distill"},{"id":"2607.28639","title":"The Asymmetric Effects of Knowledge Distillation on Bias in Small Language Models","created":"2026-05-19","cited_by_count":0,"area":"distill"},{"id":"2609.30864","title":"Persistent Negatives for Adversarial Black-Box On-Policy Distillation","created":"2026-09-25","cited_by_count":0,"area":"distill"},{"id":"2609.34447","title":"Unbiased Top-$k$ Estimation for On-Policy Distillation","created":"2026-09-28","cited_by_count":0,"area":"distill"},{"id":"2609.36695","title":"Know Thyself, Teach Thyself: Internal Information Flow for Selective Self-Distillation","created":"2026-09-29","cited_by_count":0,"area":"distill"},{"id":"2609.36734","title":"Distilling What Matters: Confidence-Aware Selective Distillation for Large Language Models","created":"2026-09-29","cited_by_count":0,"area":"distill"},{"id":"2609.39757","title":"Revisiting On-policy Adversarial Black-Box Distillation: Calibrating Groupwise Reward Geometry for Effective Advantage Construction","created":"2026-09-30","cited_by_count":0,"area":"distill"},{"id":"2610.04272","title":"Rethinking Self-Distillation for Multi-Teacher Capability Merging","created":"2026-10-03","cited_by_count":0,"area":"distill"},{"id":"2610.12837","title":"COFFEQA: Counterfactual-Guided Few-Shot Distillation for LLM Question Answering","created":"2026-10-09","cited_by_count":0,"area":"distill"}],"next_cursor":null}