Beyond the Final Layer: Intermediate Representations for Better Multilingual Calibration in Large Language Models

• URL: http://arxiv.org/abs/2510.03136v1
• Date: Fri, 03 Oct 2025 16:07:15 GMT
• Title: Beyond the Final Layer: Intermediate Representations for Better Multilingual Calibration in Large Language Models
• Authors: Ej Zhou, Caiqi Zhang, Tiancheng Hu, Chengzu Li, Nigel Collier, Ivan Vulić, Anna Korhonen,
• Abstract summary: Confidence calibration is crucial for the reliable deployment of Large Language Models (LLMs)<n>We conduct the first large-scale, systematic studies of multilingual calibration across six model families and over 100 languages.<n>We find that non-English languages suffer from systematically worse calibration.
• Score: 50.34755385896279
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Investigating the Multilingual Calibration Effects of Language Model Instruction-Tuning [58.355275813623685]
  This work looks at a critical gap in the calibration of large language models (LLMs) within multilingual settings.<n>Even in low-resource languages, model confidence can increase significantly after instruction-tuning on high-resource language SFT datasets.<n>However, improvements in accuracy are marginal or non-existent, highlighting a critical shortcoming of standard SFT for multilingual languages.
  arXiv  Detail & Related papers  (2026-01-04T04:29:12Z)
• Can Large Language Models Express Uncertainty Like Human? [71.27418419522884]
  We release the first diverse, large-scale dataset of hedging expressions with human-annotated confidence scores.<n>We conduct the first systematic study of linguistic confidence across modern large language models.
  arXiv  Detail & Related papers  (2025-09-29T02:34:30Z)
• The Hidden Space of Safety: Understanding Preference-Tuned LLMs in Multilingual context [0.9130277390156759]
  Alignment tuning has enabled large language models to excel in reasoning, instruction-following, and minimizing harmful generations.<n>Despite their widespread deployment, these models exhibit a monolingual bias, raising concerns about the effectiveness of alignment across languages.<n>Current alignment methods predominantly focus on English, leaving it unclear how alignment mechanism generalizes to multilingual settings.
  arXiv  Detail & Related papers  (2025-04-03T15:46:46Z)
• Epistemic Integrity in Large Language Models [10.50127599111102]
  Large language models are increasingly relied upon sources of information, but their propensity for false or misleading statements poses high risks for users and society.<n>In this paper, we confront the critical problem of miscalibration where a model's linguistic assertiveness fails to reflect its true internal certainty.<n>We introduce a new human misalignment evaluation and a novel method for measuring the linguistic assertiveness of Large Language Models.
  arXiv  Detail & Related papers  (2024-11-10T17:10:13Z)
• The Power of Question Translation Training in Multilingual Reasoning: Broadened Scope and Deepened Insights [108.40766216456413]
  We propose a question alignment framework to bridge the gap between large language models' English and non-English performance. Experiment results show it can boost multilingual performance across diverse reasoning scenarios, model families, and sizes. We analyze representation space, generated response and data scales, and reveal how question translation training strengthens language alignment within LLMs.
  arXiv  Detail & Related papers  (2024-05-02T14:49:50Z)
• On the Calibration of Multilingual Question Answering LLMs [57.296161186129545]
  We benchmark the calibration of several multilingual Large Language Models (MLLMs) on a variety of Question Answering tasks. We study different dimensions of calibration in in-distribution, out-of-distribution, and cross-lingual transfer settings. For decoder-only LLMs such as LlaMa2, we additionally find that in-context learning improves confidence calibration on multilingual data.
  arXiv  Detail & Related papers  (2023-11-15T03:29:02Z)
• Cross-Lingual Consistency of Factual Knowledge in Multilingual Language Models [7.478369203246005]
  We study the cross-lingual consistency (CLC) of factual knowledge in various multilingual PLMs.<n>We propose a Ranking-based Consistency (RankC) metric to evaluate knowledge consistency across languages independently from accuracy.
  arXiv  Detail & Related papers  (2023-10-16T13:19:17Z)
• On the Calibration of Massively Multilingual Language Models [15.373725507698591]
  Massively Multilingual Language Models (MMLMs) have recently gained popularity due to their surprising effectiveness in cross-lingual transfer. We first investigate the calibration of MMLMs in the zero-shot setting and observe a clear case of miscalibration in low-resource languages. We also find that few-shot examples in the language can further help reduce the calibration errors, often substantially.
  arXiv  Detail & Related papers  (2022-10-21T21:41:56Z)
• Analyzing the Mono- and Cross-Lingual Pretraining Dynamics of Multilingual Language Models [73.11488464916668]
  This study investigates the dynamics of the multilingual pretraining process. We probe checkpoints taken from throughout XLM-R pretraining, using a suite of linguistic tasks. Our analysis shows that the model achieves high in-language performance early on, with lower-level linguistic skills acquired before more complex ones.
  arXiv  Detail & Related papers  (2022-05-24T03:35:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.