paper-with-me

Papers

Compositional Subspace Representation Fine-tuning for Adaptive Large Language Models

2025-03-13 · Andy Zhou

Adapting large language models to multiple tasks can cause cross-skill interference, where improvements for one skill degrade another. While methods such as LoRA impose orthogonality constraints at the weight level, they do not fully address interference in hidden-state representations. We propose Compositional Subspace Representation Fine-tuning (CS-ReFT), a novel representation-based approach that learns multiple orthonormal subspace transformations, each specializing in a distinct skill, and composes them via a lightweight router. By isolating these subspace edits in the hidden state, rather than weight matrices, CS-ReFT prevents cross-task conflicts more effectively. On the AlpacaEval benchmark, applying CS-ReFT to Llama-2-7B achieves a 93.94% win rate, surpassing GPT-3.5 Turbo (86.30%) while requiring only 0.0098% of model parameters. These findings show that specialized representation edits, composed via a simple router, significantly enhance multi-task instruction following with minimal overhead.

📄 PDF Abstract BibTeX arXiv:2503.10617

Code (0)

등록된 구현이 없습니다.

Tasks

Instruction Following

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
{Dispute@FaQ-s}How to file a dispute with Expedia? How to file a dispute with Expedia? To file a complaint against Expedia, first try contacting their customer service directly. You can reach them by phone at…
15 Ways to Contact How can i speak to someone at Delta Airlines 설명 없음
Attention 설명 없음
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

DEFT: Decompositional Efficient Fine-Tuning for Text-to-Image Models

2025-09-26 · Komal Kumar, Rao Muhammad Anwer, Fahad Shahbaz Khan, Salman Khan 외 arxiv

Efficient fine-tuning of pre-trained Text-to-Image (T2I) models involves adjusting the model to suit a particular task or dataset while minimizing computational resources and limiting the number of trainable parameters. …

Image Generation

Dimensionality Controls When Modularity Helps in Continual Learning

2026-06-16 · Kathrin Korte, Christian Medeiros Adriano, Joachim Winther Pedersen, Eleni Nisioti 외 arxiv

Compositional learning systems must balance plasticity, the ability to acquire new knowledge, with stability, the preservation of previously learned components, especially when tasks share structure and risk interference…

Continual Learning

Adaptive Multi-Subspace Representation Steering for Attribute Alignment in Large Language Models

2025-08-14 · Xinyan Jiang, Lin Zhang, Jiayi Zhang, Qingsong Yang 외 arxiv

Activation steering offers a promising approach to controlling the behavior of Large Language Models by directly manipulating their internal activations. However, most existing methods struggle to jointly steer multiple …

Learning to Generalize Compositionally by Transferring Across Semantic Parsing Tasks

2021-11-09 · Wang Zhu, Peter Shaw, Tal Linzen, Fei Sha

Neural network models often generalize poorly to mismatched domains or distributions. In NLP, this issue arises in particular when models are expected to generalize compositionally, that is, to novel combinations of fami…

Semantic ParsingTransfer Learning

Low-rank Momentum Factorization for Memory Efficient Training

2025-07-10 · Pouria Mahdavinia, Mehrdad Mahdavi arxiv

Fine-tuning large foundation models presents significant memory challenges due to stateful optimizers like AdamW, often requiring several times more GPU memory than inference. While memory-efficient methods like paramete…

parameter-efficient fine-tuningStochastic Optimization