# RAPID: Reliability-Aware Pair Importance Distillation

arXiv: https://arxiv.org/abs/2609.05481 · HTML: https://mlsanity.com/paper/2609.05481/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Knowledge distillation for LLMs, one of 12 directions in Knowledge distillation.
- Builds on 20 of its 23 references that are in the map.
- First posted on arXiv 23 Aug 2026.

## Placed in

- Knowledge distillation / [Knowledge distillation for LLMs](https://mlsanity.com/distill/knowledge-distillation-for-llms/)

## Builds on (most cited first, 20 of 20)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [TinyBERT: Distilling BERT for Natural Language Understanding](https://mlsanity.com/paper/1909.10351/) (2019)
- [Relational Knowledge Distillation](https://mlsanity.com/paper/1904.05068/) (2019)
- [Contrastive Representation Distillation](https://mlsanity.com/paper/1910.10699/) (2019)
- [Patient Knowledge Distillation for BERT Model Compression](https://mlsanity.com/paper/1908.09355/) (2019)
- [Not All Samples Are Created Equal: Deep Learning with Importance Sampling](https://mlsanity.com/paper/1803.00942/) (2018)
- [MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformers](https://mlsanity.com/paper/2012.15828/) (2020)
- [A Survey of On-Policy Distillation for Large Language Models](https://mlsanity.com/paper/2604.00626/) (2026)
- [Too Sharp, Too Sure: When Calibration Follows Curvature](https://mlsanity.com/paper/2604.20614/) (2026)
- [KD4MT: A Survey of Knowledge Distillation for Machine Translation](https://mlsanity.com/paper/2602.15845/) (2026)
- [AMRD: Adaptive Multi-Teacher Relational Distillation for Lightweight Speech Emotion Recognition](https://mlsanity.com/paper/2607.25289/) (2026)
- [Accelerating Large Scale Knowledge Distillation via Dynamic Importance Sampling](https://mlsanity.com/paper/1812.00914/) (2018)
- [FedLAS: Feature-Modulated Bidirectional Label Smoothing for Neural Network Calibration](https://mlsanity.com/paper/2606.28654/) (2026)
- [TAKE: Trajectory-Aware Knowledge Estimation for Text Dataset Distillation](https://mlsanity.com/paper/2607.11898/) (2026)
- [Measuring Task-Agnostic Training Data Influence Across Language Model Pretraining](https://mlsanity.com/paper/2608.13515/) (2026)

## Abstract (arXiv)

Inter example relational distillation transfers a teacher's representation geometry by matching relations among examples within a mini batch. Computing all pairs has quadratic complexity in the batch size, whereas uniform subsampling may use a limited relation budget inefficiently. We introduce Reliability Aware Pair Importance Distillation, or RAPID, which separates a reliability gated relational target from a full support adaptive pair proposal. Reliability determines which teacher relations are emphasized, while calibrated teacher entropy and detached student-teacher residuals determine which relations are evaluated. Exact inverse proposal correction makes the loss and gradient estimators conditionally unbiased with respect to the gated mini batch target. We evaluate RAPID in two text classification settings: AG News with BERT-to-DistilBERT distillation using three paired seeds and a relation budget of 256, and SST-2 with DistilBERT to DistilBERT distillation using three paired seeds and a relation budget of 64. Reliability gated relational distillation achieves the highest observed mean student accuracy on both datasets: 94.285 plus or minus 0.054 percent on AG News and 88.800 plus or minus 0.532 percent on SST-2. RAPID ranks second, achieving 94.241 plus or minus 0.025 percent and 88.685 plus or minus 0.462 percent, respectively, compared with 94.154 plus or minus 0.124 percent and 87.271 plus or minus 0.162 percent for the cross entropy baseline. Pilot evaluations are counted toward the same total budget as the main relation evaluations. Across both settings, the gated target yields the highest mean accuracy, while the adaptive proposal remains within seed-level variation. These results support the modular view that target reliability and evaluation priority are separable design dimensions.