# Tevatron-Elastic: A Unified Abstraction for Training Elastic Retrievers and Rerankers

arXiv: https://arxiv.org/abs/2608.08809 · HTML: https://mlsanity.com/paper/2608.08809/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Prompt and context compression, one of 12 directions in Efficient LLM inference and serving.
- Builds on 30 of its 37 references that are in the map.
- First posted on arXiv 9 Aug 2026.

## Placed in

- Efficient LLM inference and serving / [Prompt and context compression](https://mlsanity.com/inference/prompt-and-context-compression/)

## Builds on (most cited first, 30 of 30)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval](https://mlsanity.com/paper/2007.00808/) (2020)
- [Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference](https://mlsanity.com/paper/2412.13663/) (2024)
- [RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2010.08191/) (2020)
- [DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference](https://mlsanity.com/paper/2004.12993/) (2020)
- [LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding](https://mlsanity.com/paper/2404.16710/) (2024)
- [SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking](https://mlsanity.com/paper/2107.05720/) (2021)
- [Matryoshka Representation Learning](https://mlsanity.com/paper/2205.13147/) (2022)
- [FastBERT: a Self-distilling BERT with Adaptive Inference Time](https://mlsanity.com/paper/2004.02178/) (2020)
- [Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrieval](https://mlsanity.com/paper/2108.05540/) (2021)
- [SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval](https://mlsanity.com/paper/2109.10086/) (2021)
- [SPLADE-v3: New baselines for SPLADE](https://mlsanity.com/paper/2403.06789/) (2024)
- [Tevatron 2.0: Unified Document Retrieval Toolkit across Scale, Language, and Modality](https://mlsanity.com/paper/2505.02466/) (2025)
- [A Survey of Model Architectures in Information Retrieval](https://mlsanity.com/paper/2502.14822/) (2025)
- [Hard Negatives, Hard Lessons: Revisiting Training Data Quality for Robust Information Retrieval with LLMs](https://mlsanity.com/paper/2505.16967/) (2025)
- [State Space Models are Strong Text Rerankers](https://mlsanity.com/paper/2412.14354/) (2024)
- [CSPLADE: Learned Sparse Retrieval with Causal Language Models](https://mlsanity.com/paper/2504.10816/) (2025)
- [Jasper-Token-Compression-600M Technical Report](https://mlsanity.com/paper/2511.14405/) (2025)
- [Distillation versus Contrastive Learning: How to Train Your Rerankers](https://mlsanity.com/paper/2507.08336/) (2025)
- [Beyond Correctness: Rewarding Faithful Reasoning in Retrieval-Augmented Generation](https://mlsanity.com/paper/2510.13272/) (2025)
- [LACONIC: Dense-Level Effectiveness for Scalable Sparse Retrieval via a Two-Phase Training Curriculum](https://mlsanity.com/paper/2601.01684/) (2026)
- [RECON: Reasoning with Condensation for Efficient Retrieval-Augmented Generation](https://mlsanity.com/paper/2510.10448/) (2025)
- [Rethinking On-policy Optimization for Query Augmentation](https://mlsanity.com/paper/2510.17139/) (2025)
- [Layer-wise Token Compression for Efficient Document Reranking](https://mlsanity.com/paper/2605.20683/) (2026)
- [Tevatron Meets Megatron: Expert-Parallel LLM Reranker Training on an Academic Budget](https://mlsanity.com/paper/2608.00916/) (2026)

## Abstract (arXiv)

A single model scale challenges the flexibility of a production retrieval system: some settings need it faster, others need a smaller index, and the right trade-off changes with the workload. In the context of information retrieval (IR), a transformer-based model can be made smaller in three ways---using fewer layers, passing fewer tokens through the upper layers, or producing a shorter embedding---and each way saves a different compute resource. These options have been studied one at a time, each as its own method with its own code and training setup, which makes them hard to combine or adapt to a new model. We present~ours to bring all three under one simple abstraction: a single object names any size the model can run at, and a short schedule lists the sizes to train. Training then produces one checkpoint that serves all of those sizes, and at deployment the user picks any of them. The same abstraction covers both retrievers and rerankers and both encoder and decoder models, as it works through interfaces that Hugging Face transformers already expose; a new backbone is a configuration change, not new modeling code. Prior methods---Matryoshka embeddings, early exit, 2D~Matryoshka (e.g., Starbucks), and layerwise token compression---become special cases of our unified abstraction. The same interface also enables Matryoshka~LTC (MLTC), which jointly trains several token-compression ratios in one retriever checkpoint. To validate our framework, we train 20 checkpoints across three backbones and two tasks: the quality curves are smooth, one checkpoint costs little over a model trained for a single size, and a controlled study confirms the wallclock speedups. We release the framework and all checkpoints as a resource for building elastic retrieval systems.