mlsanityData to 7 Oct 2026

RE-Adapt: Reverse Engineered Adaptation of Large Language Models

arXiv 2405.15007 ↗First posted 23 May 2024cs.CL cs.AI cs.LGcited by 9

Not on the map. Why?

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.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 30 of its 45 references that are in the map. First posted on arXiv 23 May 2024.

Builds on

30 of 45 references.

References · 30

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  4. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  5. 2017Deep reinforcement learning from human preferencescited by 3,846
  6. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  7. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  8. 2020Learning to summarize from human feedbackcited by 2,562
  9. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  10. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,462
  11. 2020AdapterFusion: Non-Destructive Task Composition for Transfer Learningcited by 780
  12. 2024DoRA: Weight-Decomposed Low-Rank Adaptationcited by 740
18 more
  1. 2021Cross-Task Generalization via Natural Language Crowdsourcing Instructionscited by 696
  2. 2023The Falcon Series of Open Language Modelscited by 526
  3. 2021Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworkscited by 278
  4. 2019Simple, Scalable Adaptation for Neural Machine Translationcited by 239
  5. 2020AdapterDrop: On the Efficiency of Adapters in Transformerscited by 223
  6. 2024Improving LoRA in Privacy-preserving Federated Learningcited by 158
  7. 2023Understanding Catastrophic Forgetting in Language Models via Implicit Inferencecited by 138
  8. 2024Seven Failure Points When Engineering a Retrieval Augmented Generation Systemcited by 138
  9. 2022AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuningcited by 137
  10. 2022StreamingQA: A Benchmark for Adaptation to New Knowledge over Time in Question Answering Modelscited by 123
  11. 2023The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reductioncited by 120
  12. 2023SLoRA: Federated Parameter Efficient Fine-Tuning of Language Modelscited by 92
  13. 2023An Emulator for Fine-Tuning Large Language Models using Small Language Modelscited by 61
  14. 2023Mixture-of-Domain-Adapters: Decoupling and Injecting Domain Knowledge to Pre-trained Language Models Memoriescited by 34
  15. 2023Cross-Lingual Transfer with Target Language-Ready Task Adapterscited by 15
  16. 2024AdapterSwap: Continuous Training of LLMs with Data Removal and Access-Control Guaranteescited by 14
  17. 2023UDApter -- Efficient Domain Adaptation Using Adapterscited by 13
  18. 2023Efficient Domain Adaptation of Sentence Embeddings Using Adapterscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 6; 2026: 2.

9 papers.

  1. 2025Shadow-FT: Tuning Instruct Model via Training on Paired Base Modelcited by 7
  2. 2025Efficient Model Development through Fine-tuning Transfercited by 6
  3. 2025SpectR: Dynamically Composing LM Experts with Spectral Routingcited by 6
  4. 2025Adapt Once, Thrive with Updates: Transferable Parameter-Efficient Fine-Tuning on Evolving Base Modelscited by 5
  5. 2025Improving Instruct Models for Free: A Study on Partial Adaptationcited by 2
  6. 2024RE-AdaptIR: Improving Information Retrieval through Reverse Engineered Adaptationcited by 1
  7. 2025IA2: Alignment with ICL Activations Improves Supervised Fine-Tuningcited by 1
  8. 2026OARS: Process-Aware Online Alignment for Generative Real-World Image Super-Resolutioncited by 1
  9. 2026GIFT: Guided Fine-Tuning and Transfer for Enhancing Instruction-Tuned Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Towards Alignment-Centric Paradigm: A Survey of Instruction Tuning in Large Language Models
  2. 2023Reflection-Tuning: Data Recycling Improves LLM Instruction-Tuning
  3. 2023kNN-Adapter: Efficient Domain Adaptation for Black-Box Language Models
  4. 2026Strategic Over-Parameterization for Generalizable Low-Rank Adaptation
  5. 2025COSMOS: Predictable and Cost-Effective Adaptation of LLMs
  6. 2026Is Human-Readable Text Necessary for Effective LLM Fine-Tuning?
  7. 2025Franken-Adapter: Cross-Lingual Adaptation of LLMs by Embedding Surgery
  8. 2025Refine-n-Judge: Curating High-Quality Preference Chains for LLM-Fine-Tuning