Cover Image

Disentangling Language Roles in Multilingual LLM Task Execution

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhan, Qishi, Hu, Minxuan, Jang, Seoyeon, Zhao, Lei, Chen, Ziheng, Liang, Man, Xiang, Xinyue, Liu, Jiaxin, Wang, Guansu, He, Liang
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Unstable Rankings in Bayesian Deep Learning Evaluation
by: Zhan, Qishi, et al.
Published: (2026)

A Tale of Two Variances: When Single-Seed Benchmarks Fail in Bayesian Deep Learning
by: Zhan, Qishi, et al.
Published: (2026)

Adaptive Signal Resuscitation: Channel-wise Post-Pruning Repair for Sparse Vision Networks
by: Zhan, Qishi, et al.
Published: (2026)

Research on Optimization of Natural Language Processing Model Based on Multimodal Deep Learning
by: Sun, Dan, et al.
Published: (2024)

Speech Recognition Model Improves Text-to-Speech Synthesis using Fine-Grained Reward
by: Wang, Guansu, et al.
Published: (2025)

Disentangling Language and Culture for Evaluating Multilingual Large Language Models
by: Ying, Jiahao, et al.
Published: (2025)

How Order-Sensitive Are LLMs? OrderProbe for Deterministic Structural Reconstruction
by: He, Yingjie, et al.
Published: (2026)

Mitigating Translationese Bias in Multilingual LLM-as-a-Judge via Disentangled Information Bottleneck
by: Zhang, Hongbin, et al.
Published: (2026)

When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual Reasoners
by: Zhao, Weixiang, et al.
Published: (2025)

EthioLLM: Multilingual Large Language Models for Ethiopian Languages with Task Evaluation
by: Tonja, Atnafu Lambebo, et al.
Published: (2024)

Lost in Execution: On the Multilingual Robustness of Tool Calling in Large Language Models
by: Luo, Zheng, et al.
Published: (2026)

Multilingual Blending: LLM Safety Alignment Evaluation with Language Mixture
by: Song, Jiayang, et al.
Published: (2024)

SPRInG: Continual LLM Personalization via Selective Parametric Adaptation and Retrieval-Interpolated Generation
by: Kim, Seoyeon, et al.
Published: (2026)

Disentangling the Roles of Target-Side Transfer and Regularization in Multilingual Machine Translation
by: Meng, Yan, et al.
Published: (2024)

From Flat Language Labels to Typological Priors: Structured Language Conditioning for Multilingual Speech-to-Speech Translation
by: Pan, Yu, et al.
Published: (2026)

From Meta-Thought to Execution: Cognitively Aligned Post-Training for Generalizable and Reliable LLM Reasoning
by: Wang, Shaojie, et al.
Published: (2026)

The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution
by: Li, Junlong, et al.
Published: (2025)

Efficient Estimation of Kernel Surrogate Models for Task Attribution
by: Zhang, Zhenshuo, et al.
Published: (2026)

Multilingual Knowledge Editing with Language-Agnostic Factual Neurons
by: Zhang, Xue, et al.
Published: (2024)

WARDEN: Endangered Indigenous Language Transcription and Translation with 6 Hours of Training Data
by: Zhang, Ziheng, et al.
Published: (2026)

AdaRubric: Task-Adaptive Rubrics for Reliable LLM Agent Evaluation and Reward Learning
by: Ding, Liang
Published: (2026)

BenchMAX: A Comprehensive Multilingual Evaluation Suite for Large Language Models
by: Huang, Xu, et al.
Published: (2025)

NCL-BU at SemEval-2026 Task 3: Fine-tuning XLM-RoBERTa for Multilingual Dimensional Sentiment Regression
by: Wu, Tong, et al.
Published: (2026)

SLIDE: A Framework Integrating Small and Large Language Models for Open-Domain Dialogues Evaluation
by: Zhao, Kun, et al.
Published: (2024)

On the Limitations of Language Targeted Pruning: Investigating the Calibration Language Impact in Multilingual LLM Pruning
by: Kurz, Simon, et al.
Published: (2024)

EuroLLM: Multilingual Language Models for Europe
by: Martins, Pedro Henrique, et al.
Published: (2024)

SparseLLM: Towards Global Pruning for Pre-trained Language Models
by: Bai, Guangji, et al.
Published: (2024)

DIALIGHT: Lightweight Multilingual Development and Evaluation of Task-Oriented Dialogue Systems with Large Language Models
by: Hu, Songbo, et al.
Published: (2024)

CM-Align: Consistency-based Multilingual Alignment for Large Language Models
by: Zhang, Xue, et al.
Published: (2025)

SoT: Structured-of-Thought Prompting Guides Multilingual Reasoning in Large Language Models
by: Qi, Rui, et al.
Published: (2025)

Overthinking Loops in Agents: A Structural Risk via MCP Tools
by: Lee, Yohan, et al.
Published: (2026)

Enhancing Large Language Models with Neurosymbolic Reasoning for Multilingual Tasks
by: Nezhad, Sina Bagheri, et al.
Published: (2025)

Cross-Lingual Transfer for Natural Language Inference via Multilingual Prompt Translator
by: Qiu, Xiaoyu, et al.
Published: (2024)

The Roles of English in Evaluating Multilingual Language Models
by: Poelman, Wessel, et al.
Published: (2024)

The Role of Mixed-Language Documents for Multilingual Large Language Model Pretraining
by: Shao, Jiandong, et al.
Published: (2026)

Is Translation All You Need? A Study on Solving Multilingual Tasks with Large Language Models
by: Liu, Chaoqun, et al.
Published: (2024)

Could Thinking Multilingually Empower LLM Reasoning?
by: Gao, Changjiang, et al.
Published: (2025)

NavCoT: Boosting LLM-Based Vision-and-Language Navigation via Learning Disentangled Reasoning
by: Lin, Bingqian, et al.
Published: (2024)

Python Symbolic Execution with LLM-powered Code Generation
by: Wang, Wenhan, et al.
Published: (2024)

Information Loss in LLMs' Multilingual Translation: The Role of Training Data, Language Proximity, and Language Family
by: Lin, Yumeng, et al.
Published: (2025)