Cover Image

To MRL or not to MRL: Text Embeddings are Robust to Truncation Without Matryoshka Learning, Except In Heavy Truncation Scenarios

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Takeshita, Sotaro, Takeshita, Yurina, Ponzetto, Simone Paolo, Ruffinelli, Daniel
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Randomly Removing 50% of Dimensions in Text Embeddings has Minimal Impact on Retrieval and Classification Tasks
by: Takeshita, Sotaro, et al.
Published: (2025)

ROUGE-K: Do Your Summaries Have Keywords?
by: Takeshita, Sotaro, et al.
Published: (2024)

MRL Parsing Without Tears: The Case of Hebrew
by: Shmidman, Shaltiel, et al.
Published: (2024)

ACLSum: A New Dataset for Aspect-based Summarization of Scientific Publications
by: Takeshita, Sotaro, et al.
Published: (2024)

Enriching Social Science Research via Survey Item Linking
by: Tsereteli, Tornike, et al.
Published: (2024)

2D Matryoshka Sentence Embeddings
by: Li, Xianming, et al.
Published: (2024)

SMEC: Rethinking Matryoshka Representation Learning for Retrieval Embedding Compression
by: Zhang, Biao, et al.
Published: (2025)

Fewer Truncations Improve Language Modeling
by: Ding, Hantian, et al.
Published: (2024)

Matryoshka-Adaptor: Unsupervised and Supervised Tuning for Smaller Embedding Dimensions
by: Yoon, Jinsung, et al.
Published: (2024)

Steering Language Models in Multi-Token Generation: A Case Study on Tense and Aspect
by: Klerings, Alina, et al.
Published: (2025)

STAR: Spectral Truncation and Rescale for Model Merging
by: Lee, Yu-Ang, et al.
Published: (2025)

DyMRL: Dynamic Multispace Representation Learning for Multimodal Event Forecasting in Knowledge Graph
by: Zhao, Feng, et al.
Published: (2026)

FedMRL: Data Heterogeneity Aware Federated Multi-agent Deep Reinforcement Learning for Medical Imaging
by: Sahoo, Pranab, et al.
Published: (2024)

Private Language Models via Truncated Laplacian Mechanism
by: Huang, Tianhao, et al.
Published: (2024)

Geometry-Aware Decoding with Wasserstein-Regularized Truncation and Mass Penalties for Large Language Models
by: Davoodi, Arash Gholami, et al.
Published: (2026)

SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compression
by: Wang, Xin, et al.
Published: (2024)

The Truncation Blind Spot: How Decoding Strategies Systematically Exclude Human-Like Token Choices
by: Arias, Esteban Garces, et al.
Published: (2026)

Culturally Grounded Physical Commonsense Reasoning in Italian and English: A Submission to the MRL 2025 Shared Task
by: De Santis, Marco, et al.
Published: (2025)

SandboxAQ's submission to MRL 2024 Shared Task on Multi-lingual Multi-task Information Retrieval
by: Tourni, Isidora Chara, et al.
Published: (2024)

ROCKET: Rapid Optimization via Calibration-guided Knapsack Enhanced Truncation for Efficient Model Compression
by: Ali, Ammar, et al.
Published: (2026)

Min-$k$ Sampling: Decoupling Truncation from Temperature Scaling via Relative Logit Dynamics
by: Ding, Yuanhao, et al.
Published: (2026)

Matryoshka Pilot: Learning to Drive Black-Box LLMs with LLMs
by: Li, Changhao, et al.
Published: (2024)

GerAV: Towards New Heights in German Authorship Verification using Fine-Tuned LLMs on a New Benchmark
by: Kiefer, Lotta, et al.
Published: (2026)

Matryoshka Multimodal Models
by: Cai, Mu, et al.
Published: (2024)

RobustSentEmbed: Robust Sentence Embeddings Using Adversarial Self-Supervised Contrastive Learning
by: Asl, Javad Rafiei, et al.
Published: (2024)

Error Norm Truncation: Robust Training in the Presence of Data Noise for Text Generation Models
by: Li, Tianjian, et al.
Published: (2023)

Challenging Assumptions in Learning Generic Text Style Embeddings
by: Ostheimer, Phil, et al.
Published: (2025)

Matryoshka Query Transformer for Large Vision-Language Models
by: Hu, Wenbo, et al.
Published: (2024)

MatMamba: A Matryoshka State Space Model
by: Shukla, Abhinav, et al.
Published: (2024)

Ranked List Truncation for Large Language Model-based Re-Ranking
by: Meng, Chuan, et al.
Published: (2024)

Arctic-Embed 2.0: Multilingual Retrieval Without Compromise
by: Yu, Puxuan, et al.
Published: (2024)

MatryoshkaLoRA: Learning Accurate Hierarchical Low-Rank Representations for LLM Fine-Tuning
by: Modoranu, Ionut-Vlad, et al.
Published: (2026)

MatryoshkaKV: Adaptive KV Compression via Trainable Orthogonal Projection
by: Lin, Bokai, et al.
Published: (2024)

On the Noise Robustness of In-Context Learning for Text Generation
by: Gao, Hongfu, et al.
Published: (2024)

Truncated Consistency Models
by: Lee, Sangyun, et al.
Published: (2024)

Factor Augmented Supervised Learning with Text Embeddings
by: Luo, Zhanye, et al.
Published: (2025)

An Improved Deep Learning Model for Word Embeddings Based Clustering for Large Text Datasets
by: Sutrakar, Vijay Kumar, et al.
Published: (2025)

On Debiasing Text Embeddings Through Context Injection
by: Uriot, Thomas
Published: (2024)

Differentially Private Online Bayesian Estimation With Adaptive Truncation
by: Yıldırım, Sinan
Published: (2023)

A Large-Scale Sensitivity Analysis on Latent Embeddings and Dimensionality Reductions for Text Spatializations
by: Atzberger, Daniel, et al.
Published: (2024)