Beyond the Final Layer: Intermediate Representations for Better Multilingual Calibration in Large Language Models
Abstract
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.
Cite
@article{arxiv.2510.03136,
title = {Beyond the Final Layer: Intermediate Representations for Better Multilingual Calibration in Large Language Models},
author = {Ej Zhou and Caiqi Zhang and Tiancheng Hu and Chengzu Li and Nigel Collier and Ivan Vulić and Anna Korhonen},
journal= {arXiv preprint arXiv:2510.03136},
year = {2025}
}