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

arXiv:2510.03136 · cs.CL · Submitted 2025-10-03 · Read on arXiv

cs.CL

Submitted: 2025-10-03

Updated: 2026-08-31

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Calibration — 132× in this paper · explained in 7 episodes
• Accuracy — 38× in this paper · explained in 1 episode
• Alignment — 12× in this paper · explained in 1 episode
• Benchmark — 5× in this paper · explained in 2 episodes
• Language-Aware Confidence Ensemble — 5× in this paper
• Transformer — 5× in this paper · explained in 2 episodes
• Low-Resource Languages — 4× in this paper · explained in 4 episodes
• Expected Calibration Error — 3× in this paper
• Large Language Models (LLMs) — 2× in this paper · explained in 6 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Algorithmic Bias — 1× in this paper · explained in 1 episode
• Core — 1× in this paper · explained in 2 episodes
• Cross-lingual Transfer — 1× in this paper · explained in 2 episodes
• Ensemble Approach — 1× in this paper · explained in 3 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Multiple-Choice Question-Answering — 1× in this paper
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Uncertainty Quantification — 1× in this paper · explained in 8 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Phi-4 Technical Report
• Layer Swapping for Zero-Shot Cross-Lingual Transfer in Large Language Models
• The harms of class imbalance corrections for machine learning based prediction models: a simulation study
• Mind the Confidence Gap: Overconfidence, Calibration, and Distractor Effects in Large Language Models
• Aya Expanse: Combining Research Breakthroughs for a New Multilingual Frontier
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• A Comparative Study of Confidence Calibration in Deep Learning: From Computer Vision to Medical Imaging
• The Llama 3 Herd of Models
• Qwen2 Technical Report
• LoGU: Long-form Generation with Uncertainty Expressions

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering