RE-Adapt: Reverse Engineered Adaptation of Large Language Models
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Instruction FollowingRetrievalRetrieval-augmented GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
RE-AdaptIR: Improving Information Retrieval through Reverse Engineered Adaptation
Large language models (LLMs) fine-tuned for text-retrieval have demonstrated state-of-the-art results across several information retrieval (IR) benchmarks. However, supervised training for improving these models requires…
Information RetrievalRetrievalText RetrievalLLM4CodeRE: Generative AI for Code Decompilation Analysis and Reverse Engineering
Code decompilation analysis is a fundamental yet challenging task in malware reverse engineering, particularly due to the pervasive use of sophisticated obfuscation techniques. Although recent large language models (LLMs…
Classification of Reverse-Engineered Class Diagram and Forward-Engineered Class Diagram using Machine Learning
UML Class diagram is very important to visualize the whole software we are working on and helps understand the whole system in the easiest way possible by showing the system classes, its attributes, methods, and relation…
BIG-bench Machine LearningGeneral ClassificationVPA: Fully Test-Time Visual Prompt Adaptation
Textual prompt tuning has demonstrated significant performance improvements in adapting natural language processing models to a variety of downstream tasks by treating hand-engineered prompts as trainable parameters. Ins…
Domain AdaptationPseudo LabelTest-time AdaptationVisual Prompting+2Learning to Learn-at-Test-Time: Language Agents with Learnable Adaptation Policies
Test-Time Learning (TTL) enables language agents to iteratively refine their performance through repeated interactions with the environment at inference time. At the core of TTL is an adaptation policy that updates the a…