paper-with-me

홈 › Papers

SPEAR-MM: Selective Parameter Evaluation and Restoration via Model Merging for Efficient Financial LLM Adaptation

2025-11-11 · Berkcan Kapusuzoglu, Supriyo Chakraborty, Renkun Ni, Stephen Rawls, Sambit Sahu arxiv

Large language models (LLMs) adapted to financial domains often suffer from catastrophic forgetting of general reasoning capabilities essential for customer interactions and complex financial analysis. We introduce Selective Parameter Evaluation and Restoration via Model Merging (SPEAR-MM), a practical framework that preserves critical capabilities while enabling domain adaptation. Our method approximates layer-wise impact on external benchmarks through post-hoc analysis, then selectively freezes or restores transformer layers via spherical interpolation merging. Applied to LLaMA-3.1-8B for financial tasks, SPEAR-MM achieves 91.2% retention of general capabilities versus 69.7% for standard continual pretraining, while maintaining 94% of domain adaptation gains. The approach provides interpretable trade-off control and reduces computational costs by 90% crucial for resource-constrained financial institutions.

📄 PDF Abstract BibTeX arXiv:2511.08500

Code (0)

등록된 구현이 없습니다.

Tasks

Continual PretrainingDomain Adaptation

Similar Papers 제목 키워드 기반

LaverNet: Lightweight All-in-one Video Restoration via Selective Propagation

2025-12-18 · Haiyu Zhao, Yiwen Shan, Yuanbiao Gou, Xi Peng arxiv

Recent studies have explored all-in-one video restoration, which handles multiple degradations with a unified model. However, these approaches still face two challenges when dealing with time-varying degradations. First,…

Video Restoration

Learning Adaptive Dynamical Features via Multi-$τ$ Liquid-Mamba for All-in-one Image Restoration

2026-06-22 · Hu Gao, Changshuo Wang, Yulong Chen, Lizhuang Ma arxiv

Image restoration aims to recover high-quality images from degraded observations. Recent Mamba-based image restoration models have demonstrated strong potential in modeling long-range dependencies with linear complexity.…

Image Restoration

“Shakespeare in the Vectorian Age” – An evaluation of different word embeddings and NLP parameters for the detection of Shakespeare quotes

2020-12-01 · COLING (LaTeCHCLfL, CLFL, LaTeCH) 2020 12 · Bernhard Liebl, Manuel Burghardt

In this paper we describe an approach for the computer-aided identification of Shakespearean intertextuality in a corpus of contemporary fiction. We present the Vectorian, which is a framework that implements different w…

Word Embeddings

VmambaIR: Visual State Space Model for Image Restoration

2024-03-18 · Yuan Shi, Bin Xia, Xiaoyu Jin, Xing Wang 외

Image restoration is a critical task in low-level computer vision, aiming to restore high-quality images from degraded inputs. Various models, such as convolutional neural networks (CNNs), generative adversarial networks…

DenoisingImage RestorationImage Super-Resolutionmodel+3

Curvature-Aware Safety Restoration In LLMs Fine-Tuning

2025-11-22 · Thong Bach, Thanh Nguyen-Tang, Dung Nguyen, Thao Minh Le 외 arxiv

Fine-tuning Large Language Models (LLMs) for downstream tasks often compromises safety alignment, even when using parameter-efficient methods like LoRA. In this work, we uncover a notable property: fine-tuned models pres…

Few-Shot Learning