Cover Image

GAPrune: Gradient-Alignment Pruning for Domain-Aware Embeddings

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tang, Yixuan, Yang, Yi
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Do We Need Domain-Specific Embedding Models? An Empirical Investigation
by: Tang, Yixuan, et al.
Published: (2024)

KV-Embedding: Training-free Text Embedding via Internal KV Re-routing in Decoder-only LLMs
by: Tang, Yixuan, et al.
Published: (2026)

SR-GRPO: Stable Rank as an Intrinsic Geometric Reward for Large Language Model Alignment
by: Tang, Yixuan, et al.
Published: (2025)

FinMTEB: Finance Massive Text Embedding Benchmark
by: Tang, Yixuan, et al.
Published: (2025)

Pooling And Attention: What Are Effective Designs For LLM-Based Embedding Models?
by: Tang, Yixuan, et al.
Published: (2024)

Revealing the Numeracy Gap: An Empirical Investigation of Text Embedding Models
by: Deng, Ningyuan, et al.
Published: (2025)

MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries
by: Tang, Yixuan, et al.
Published: (2024)

Crowded in B-Space: Calibrating Shared Directions for LoRA Merging
by: Tang, Yixuan, et al.
Published: (2026)

AI Research Agents Narrow Scientific Exploration
by: Tang, Yixuan, et al.
Published: (2026)

Mind the Shift: Decoding Monetary Policy Stance from FOMC Statements with Large Language Models
by: Tang, Yixuan, et al.
Published: (2026)

Improving Weak-to-Strong Generalization with Reliability-Aware Alignment
by: Guo, Yue, et al.
Published: (2024)

GradMAP: Faster Layer Pruning with Gradient Metric and Projection Compensation
by: Liu, Hao, et al.
Published: (2026)

PersonaFuse: A Personality Activation-Driven Framework for Enhancing Human-LLM Interactions
by: Tang, Yixuan, et al.
Published: (2025)

Know the Unknown: An Uncertainty-Sensitive Method for LLM Instruction Tuning
by: Li, Jiaqi, et al.
Published: (2024)

Personality Alignment of Large Language Models
by: Zhu, Minjun, et al.
Published: (2024)

Reinforced Curriculum Pre-Alignment for Domain-Adaptive VLMs
by: Yan, Yuming, et al.
Published: (2026)

Pruning as a Domain-specific LLM Extractor
by: Zhang, Nan, et al.
Published: (2024)

Learning to Focus: Causal Attention Distillation via Gradient-Guided Token Pruning
by: Guo, Yiju, et al.
Published: (2025)

Improving Generalization in LLM Structured Pruning via Function-Aware Neuron Grouping
by: Yu, Tao, et al.
Published: (2025)

Your Weak LLM is Secretly a Strong Teacher for Alignment
by: Tao, Leitian, et al.
Published: (2024)

Length-Aware Rotary Position Embedding for Text-Speech Alignment
by: Kim, Hyeongju, et al.
Published: (2025)

Sink-Aware Pruning for Diffusion Language Models
by: Myrzakhan, Aidar, et al.
Published: (2026)

EfficientXpert: Efficient Domain Adaptation for Large Language Models via Propagation-Aware Pruning
by: Zhao, Songlin, et al.
Published: (2025)

Safety Alignment as Continual Learning: Mitigating the Alignment Tax via Orthogonal Gradient Projection
by: Sun, Guanglong, et al.
Published: (2026)

Iterative Structured Pruning for Large Language Models with Multi-Domain Calibration
by: Wu, Guangxin, et al.
Published: (2026)

CASE -- Condition-Aware Sentence Embeddings for Conditional Semantic Textual Similarity Measurement
by: Zhang, Gaifan, et al.
Published: (2025)

Pruning as Regularization: Sensitivity-Aware One-Shot Pruning in ASR
by: Irigoyen, Julian, et al.
Published: (2025)

How Useful is Continued Pre-Training for Generative Unsupervised Domain Adaptation?
by: Uppaal, Rheeya, et al.
Published: (2024)

FLARE: Task-agnostic embedding model evaluation through a normalization process
by: Jiang, Jingzhou, et al.
Published: (2026)

IG-Pruning: Input-Guided Block Pruning for Large Language Models
by: Qiao, Kangyu, et al.
Published: (2025)

EmbedGrad: Gradient-Based Prompt Optimization in Embedding Space for Large Language Models
by: Hou, Xiaoming, et al.
Published: (2025)

CONGRAD:Conflicting Gradient Filtering for Multilingual Preference Alignment
by: Li, Jiangnan, et al.
Published: (2025)

Wanda++: Pruning Large Language Models via Regional Gradients
by: Yang, Yifan, et al.
Published: (2025)

Alignment-Constrained Dynamic Pruning for LLMs: Identifying and Preserving Alignment-Critical Circuits
by: Patel, Dev, et al.
Published: (2025)

Modality-Aware Neuron Pruning for Unlearning in Multimodal Large Language Models
by: Liu, Zheyuan, et al.
Published: (2025)

Benchmarking Cross-Lingual Semantic Alignment in Multilingual Embeddings
by: Gong, Wen G.
Published: (2025)

PAT: Pruning-Aware Tuning for Large Language Models
by: Liu, Yijiang, et al.
Published: (2024)

Using Optimal Transport as Alignment Objective for fine-tuning Multilingual Contextualized Embeddings
by: Alqahtani, Sawsan, et al.
Published: (2021)

Evaluating and Aligning Human Economic Risk Preferences in LLMs
by: Liu, Jiaxin, et al.
Published: (2025)

Towards Domain Specification of Embedding Models in Medicine
by: Khodadad, Mohammad, et al.
Published: (2025)