# RE-Adapt: Reverse Engineered Adaptation of Large Language Models

arXiv: https://arxiv.org/abs/2405.15007 · HTML: https://mlsanity.com/paper/2405.15007/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 45 references that are in the map.
- First posted on arXiv 23 May 2024.

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

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [AdapterFusion: Non-Destructive Task Composition for Transfer Learning](https://mlsanity.com/paper/2005.00247/) (2020)
- [DoRA: Weight-Decomposed Low-Rank Adaptation](https://mlsanity.com/paper/2402.09353/) (2024)
- [Cross-Task Generalization via Natural Language Crowdsourcing Instructions](https://mlsanity.com/paper/2104.08773/) (2021)
- [The Falcon Series of Open Language Models](https://mlsanity.com/paper/2311.16867/) (2023)
- [Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks](https://mlsanity.com/paper/2106.04489/) (2021)
- [Simple, Scalable Adaptation for Neural Machine Translation](https://mlsanity.com/paper/1909.08478/) (2019)
- [AdapterDrop: On the Efficiency of Adapters in Transformers](https://mlsanity.com/paper/2010.11918/) (2020)
- [Improving LoRA in Privacy-preserving Federated Learning](https://mlsanity.com/paper/2403.12313/) (2024)
- [Understanding Catastrophic Forgetting in Language Models via Implicit Inference](https://mlsanity.com/paper/2309.10105/) (2023)
- [Seven Failure Points When Engineering a Retrieval Augmented Generation System](https://mlsanity.com/paper/2401.05856/) (2024)
- [AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning](https://mlsanity.com/paper/2210.17451/) (2022)
- [StreamingQA: A Benchmark for Adaptation to New Knowledge over Time in Question Answering Models](https://mlsanity.com/paper/2205.11388/) (2022)
- [The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction](https://mlsanity.com/paper/2312.13558/) (2023)
- [SLoRA: Federated Parameter Efficient Fine-Tuning of Language Models](https://mlsanity.com/paper/2308.06522/) (2023)
- [An Emulator for Fine-Tuning Large Language Models using Small Language Models](https://mlsanity.com/paper/2310.12962/) (2023)
- [Mixture-of-Domain-Adapters: Decoupling and Injecting Domain Knowledge to Pre-trained Language Models Memories](https://mlsanity.com/paper/2306.05406/) (2023)
- [Cross-Lingual Transfer with Target Language-Ready Task Adapters](https://mlsanity.com/paper/2306.02767/) (2023)
- [AdapterSwap: Continuous Training of LLMs with Data Removal and Access-Control Guarantees](https://mlsanity.com/paper/2404.08417/) (2024)
- [UDApter -- Efficient Domain Adaptation Using Adapters](https://mlsanity.com/paper/2302.03194/) (2023)
- [Efficient Domain Adaptation of Sentence Embeddings Using Adapters](https://mlsanity.com/paper/2307.03104/) (2023)

## Built on by (most cited first, 9 of 9)

- [Shadow-FT: Tuning Instruct Model via Training on Paired Base Model](https://mlsanity.com/paper/2505.12716/) (2025)
- [Efficient Model Development through Fine-tuning Transfer](https://mlsanity.com/paper/2503.20110/) (2025)
- [SpectR: Dynamically Composing LM Experts with Spectral Routing](https://mlsanity.com/paper/2504.03454/) (2025)
- [Adapt Once, Thrive with Updates: Transferable Parameter-Efficient Fine-Tuning on Evolving Base Models](https://mlsanity.com/paper/2506.06844/) (2025)
- [Improving Instruct Models for Free: A Study on Partial Adaptation](https://mlsanity.com/paper/2504.11626/) (2025)
- [RE-AdaptIR: Improving Information Retrieval through Reverse Engineered Adaptation](https://mlsanity.com/paper/2406.14764/) (2024)
- [IA2: Alignment with ICL Activations Improves Supervised Fine-Tuning](https://mlsanity.com/paper/2509.22621/) (2025)
- [OARS: Process-Aware Online Alignment for Generative Real-World Image Super-Resolution](https://mlsanity.com/paper/2603.12811/) (2026)
- [GIFT: Guided Fine-Tuning and Transfer for Enhancing Instruction-Tuned Language Models](https://mlsanity.com/paper/2605.01256/) (2026)

## Abstract (arXiv)

We introduce RE-Adapt, an approach to fine-tuning large language models on new domains without degrading any pre-existing instruction-tuning. We reverse engineer an adapter which isolates what an instruction-tuned model has learned beyond its corresponding pretrained base model. Importantly, this requires no additional data or training. We can then fine-tune the base model on a new domain and readapt it to instruction following with the reverse engineered adapter. RE-Adapt and our low-rank variant LoRE-Adapt both outperform other methods of fine-tuning, across multiple popular LLMs and datasets, even when the models are used in conjunction with retrieval-augmented generation.