Confidence calibration, the alignment of a model's predicted confidence with its actual accuracy, is crucial for the reliable deployment of Large Language Models (LLMs). However, this critical property remains largely under-explored in multilingual contexts. In this work, we conduct the first large-scale, systematic studies of multilingual calibration across six model families and over 100 languages, revealing that non-English languages suffer from systematically worse calibration. To diagnose this, we investigate the model's internal representations and find that the final layer, biased by English-centric training, provides a poor signal for multilingual confidence. In contrast, our layer-wise analysis uncovers a key insight that late-intermediate layers consistently offer a more reliable and better-calibrated signal. Building on this, we introduce a suite of training-free methods, including Language-Aware Confidence Ensemble (LACE), which adaptively selects an optimal ensemble of layers for each specific language. Our study highlights the hidden costs of English-centric alignment and offer a new path toward building more globally equitable and trustworthy LLMs by looking beyond the final layer.
Multilingual Brain Surgeon: Large Language Models Can be Compressed Leaving No Language Behind
X-LANCE Lab, Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence, SJTU AI Institute Shanghai Jiao Tong University, Shanghai, China（X-LANCE实验室，计算机科学与工程系，MoE人工智能关键实验室，上海交通大学人工智能研究院，上海，中国）；Suzhou Laboratory, Suzhou, China（苏州实验室，苏州，中国）
Investigating the Multilingual Calibration Effects of Language Model Instruction-Tuning
Mila - Quebec AI Institute（魁北克人工智能研究所）；Université de Montréal（蒙特利尔大学）；The University of Tokyo（东京大学）；Western University（西方大学）；Vector Institute（向量研究所）；Polytechnique Montréal（蒙特利尔理工学院）；CIFAR AI Chair（CIFAR人工智能主席）；AIST（日本产业技术综合研究所）
On the Limitations of Language Targeted Pruning: Investigating the Calibration Language Impact in Multilingual LLM Pruning
Department of Computer Science, TU Dortmund University（图恩-多特蒙德大学计算机科学系）；Bonn-Aachen International Center for Information Technology, University of Bonn（波恩-亚琛国际信息科技中心，波恩大学）；Computer Science School, University of Sheffield（谢菲尔德大学计算机科学学院）；Lamarr Institute for Machine Learning and Artificial Intelligence（拉马尔人工智能与机器学习研究所）
Lost in Reordering: Structural Sensitivity of Multilingual LLMs under Semantics-Preserving Perturbations
Indian Institute of Technology Bombay（印度理工学院孟买分校）；Indian Institute of Technology Mandi（印度理工学院曼迪分校）；Indian Institute of Technology Hyderabad（印度理工学院海得拉巴分校）
Reliable Multilingual Orthopedic Decision Support from Clinical Narratives: Language-Aware Adaptation and Verification-Guided Deferral
School of Computer Science, Wuhan University（武汉大学计算机学院）；School of Software, Nanjing University of Information Science and Technology (NUIST)（南京信息工程大学软件学院）；Department of Orthopedic, Bahawal Victoria Hospital（巴哈瓦尔维多利亚医院骨科部门）
N2C2: Nearest Neighbor Enhanced Confidence Calibration for Cross-Lingual In-Context Learning
School of Informatics, University of Edinburgh（爱丁堡大学信息学院）；School of Computer Science and Informatics, Cardiff University（卡迪夫大学计算机科学与信息学院）；College of Intelligence and Computing, Tianjin University（天津大学智能与计算学部）
MultiLingPoT: Enhancing Mathematical Reasoning with Multilingual Program Fine-tuning
Fudan University（复旦大学）；MYbank, Ant Group（蚂蚁集团MYbank）；School of Computer Science, Fudan University（复旦大学计算机学院）；School of Data Science, Fudan University（复旦大学数据科学学院）
Utilizing Multilingual Encoders to Improve Large Language Models for Low-Resource Languages
School of Mathematical and Computational Sciences, Massey University, Auckland, New Zealand（数学与计算科学学院，梅西大学，奥克兰，新西兰）；Department of Computer Science, The Open University, Milton Keynes, United Kingdom（计算机科学系，开放大学，米利顿凯斯，英国）
Evaluating Large Language Model with Knowledge Oriented Language Specific Simple Question Answering
Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Peking University（北京大学）；University of Chinese Academy of Sciences（中国科学院大学）；Shanghai University（上海大学）
RomanLens: The Role Of Latent Romanization In Multilinguality In LLMs
Nilekani Centre at AI4Bharat（AI4Bharat 奈尔肯中心）；Singapore University of Technology and Design（新加坡科技设计大学）；Indian Institute of Technology Madras（印度理工学院马德拉斯分校）；National Institute of Information and Communications Technology（信息与通信技术国家研究所）；Indian Institute of Technology Bombay（印度理工学院孟买分校）；Microsoft（微软）；IT University of Copenhagen（哥本哈根IT大学）
Indic-TunedLens: Interpreting Multilingual Models in Indian Languages
Dwarkadas Jivanlal Sanghvi College of Engineering（达沃拉斯·吉文拉尔工程学院）；Indian Institute of Technology Jodhpur（印度理工学院乔浦尔分校）；King’s College London（伦敦国王学院）；Indian Institute of Technology Patna（印度理工学院帕特纳分校）
CodePivot: Bootstrapping Multilingual Transpilation in LLMs via Reinforcement Learning without Parallel Corpora
The Hong Kong University of Science and Technology（香港科学与技术大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州））；Monash University（莫纳什大学）；The Chinese University of Hong Kong（香港中文大学）
MONICA: Real-Time Monitoring and Calibration of Chain-of-Thought Sycophancy in Large Reasoning Models
University of Bristol（布里斯托大学）；King Abdullah University of Science and Technology（卡利斯勒国王大学科学与技术学院）；University of Georgia（佐治亚大学）；Southern University of Science and Technology（南方科技大学）
Multilingual Word Embeddings for Low-Resource Languages using Anchors and a Chain of Related Languages
Center for Information and Language Processing, LMU Munich（慕尼黑大学信息与语言处理中心）；Munich Center for Machine Learning（慕尼黑机器学习中心）；Technical University of Munich（慕尼黑工业大学）
Training Multilingual Machine Translation by Alternately Freezing Language-Specific Encoders-Decoders
TALP Research Center（TALP研究中心）；Universitat Politècnica de Catalunya（加泰罗尼亚理工大学）；IXA NLP Group（IXA自然语言处理组）；University of the Basque Country (UPV/EHU)（巴斯克大学（UPV/EHU））
