Imagen de Portada

One Language, Two Scripts: Probing Script-Invariance in LLM Concept Representations

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Karne, Sripad
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

How Far Do Auto-Interpretation Labels Generalize: A Controlled Study Across Languages, Scripts, and Rewordings
por: Karne, Sripad
Publicado: (2026)

The Effect of Scripts and Formats on LLM Numeracy
por: Reddy, Varshini, et al.
Publicado: (2026)

Script-Agnostic Language Identification
por: Agarwal, Milind, et al.
Publicado: (2024)

Unknown Script: Impact of Script on Cross-Lingual Transfer
por: Tufa, Wondimagegnhue Tsegaye, et al.
Publicado: (2024)

One Script Instead of Hundreds? On Pretraining Romanized Encoder Language Models
por: Ebing, Benedikt, et al.
Publicado: (2026)

Script Sensitivity: Benchmarking Language Models on Unicode, Romanized and Mixed-Script Sinhala
por: Rajapakse, Minuri, et al.
Publicado: (2026)

SkyScript-100M: 1,000,000,000 Pairs of Scripts and Shooting Scripts for Short Drama
por: Tang, Jing, et al.
Publicado: (2024)

Script Gap: Evaluating LLM Triage on Indian Languages in Native vs Romanized Scripts in a Real World Setting
por: Khullar, Manurag, et al.
Publicado: (2025)

SN-WER: Script-Normalized WER for Multi-Script Indic ASR Evaluation
por: Pattnayak, Priyaranjan
Publicado: (2026)

IITR-CIOL@NLU of Devanagari Script Languages 2025: Multilingual Hate Speech Detection and Target Identification in Devanagari-Scripted Languages
por: Gupta, Siddhant, et al.
Publicado: (2024)

ILID: Native Script Language Identification for Indian Languages
por: Ingle, Yash, et al.
Publicado: (2025)

LangSAMP: Language-Script Aware Multilingual Pretraining
por: Liu, Yihong, et al.
Publicado: (2024)

A Tale of Two Scripts: Transliteration and Post-Correction for Judeo-Arabic
por: Gonzalez, Juan Moreno, et al.
Publicado: (2025)

Linear Script Representations in Speech Foundation Models Enable Zero-Shot Transliteration
por: Shim, Ryan Soh-Eun, et al.
Publicado: (2026)

Breaking the Script Barrier: Enabling Automatic Alignment for PoS-based ASR Error Analysis in Non-Latin Scripts
por: Mudi, Prasenjit K, et al.
Publicado: (2026)

MIXAR: Scaling Autoregressive Pixel-based Language Models to Multiple Languages and Scripts
por: Hu, Chen, et al.
Publicado: (2026)

The Latin Substrate: How Language Models Represent and Mediate Script Choice
por: Gurgurov, Daniil, et al.
Publicado: (2026)

Konkani LLM: Multi-Script Instruction Tuning and Evaluation for a Low-Resource Indian Language
por: Fernandes, Reuben Chagas, et al.
Publicado: (2026)

Multilingual Language Models Encode Script Over Linguistic Structure
por: Verma, Aastha A K, et al.
Publicado: (2026)

Machine-Assisted Script Curation
por: Ciosici, Manuel R., et al.
Publicado: (2021)

Simple Additions, Substantial Gains: Expanding Scripts, Languages, and Lineage Coverage in URIEL+
por: Shipton, Mason, et al.
Publicado: (2025)

UniGlyph: A Seven-Segment Script for Universal Language Representation
por: Sherin, G. V. Bency, et al.
Publicado: (2024)

Select and Summarize: Scene Saliency for Movie Script Summarization
por: Saxena, Rohit, et al.
Publicado: (2024)

Evaluating Shortest Edit Script Methods for Contextual Lemmatization
por: Toporkov, Olia, et al.
Publicado: (2024)

ScEdit: Script-based Assessment of Knowledge Editing
por: Li, Xinye, et al.
Publicado: (2025)

Multilingual Dialogue Generation and Localization with Dialogue Act Scripting
por: Vasselli, Justin, et al.
Publicado: (2025)

MultiScript30k: Leveraging Multilingual Embeddings to Extend Cross Script Parallel Data
por: Driggers-Ellis, Christopher, et al.
Publicado: (2025)

EcomScriptBench: A Multi-task Benchmark for E-commerce Script Planning via Step-wise Intention-Driven Product Association
por: Wang, Weiqi, et al.
Publicado: (2025)

Nile-Chat: Egyptian Language Models for Arabic and Latin Scripts
por: Shang, Guokan, et al.
Publicado: (2025)

The Role of Orthographic Consistency in Multilingual Embedding Models for Text Classification in Arabic-Script Languages
por: Abdullah, Abdulhady Abas, et al.
Publicado: (2025)

CML-Bench: A Framework for Evaluating and Enhancing LLM-Powered Movie Scripts Generation
por: Zheng, Mingzhe, et al.
Publicado: (2025)

Reasoning Over the Glyphs: Evaluation of LLM's Decipherment of Rare Scripts
por: Shih, Yu-Fei, et al.
Publicado: (2025)

Bolbosh: Script-Aware Flow Matching for Kashmiri Text-to-Speech
por: Ashraf, Tajamul, et al.
Publicado: (2026)

Multimedia Generative Script Learning for Task Planning
por: Wang, Qingyun, et al.
Publicado: (2022)

Contrastive-to-Self-Supervised: A Two-Stage Framework for Script Similarity Learning
por: Roman, Claire, et al.
Publicado: (2026)

Read the Scene, Not the Script: Outcome-Aware Safety for LLMs
por: Wu, Rui, et al.
Publicado: (2025)

Multi-class Regret Detection in Hindi Devanagari Script
por: Sharma, Renuka, et al.
Publicado: (2024)

Prompting with Phonemes: Enhancing LLMs' Multilinguality for Non-Latin Script Languages
por: Nguyen, Hoang H, et al.
Publicado: (2024)

Classification of Spontaneous and Scripted Speech for Multilingual Audio
por: Elisha, Shahar, et al.
Publicado: (2024)

Enabling Stroke-Level Structural Analysis of Hieroglyphic Scripts without Language-Specific Priors
por: Luo, Fuwen, et al.
Publicado: (2026)