Copertina

Calibration Is Not Enough: Evaluating Confidence Estimation Under Language Variations

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Xia, Yuxi, Ulmer, Dennis, Blevins, Terra, Liu, Yihong, Schütze, Hinrich, Roth, Benjamin
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Evaluating Contextually Mediated Factual Recall in Multilingual Large Language Models
di: Liu, Yihong, et al.
Pubblicazione: (2026)

Do language models accommodate their users? A study of linguistic convergence
di: Blevins, Terra, et al.
Pubblicazione: (2025)

Accommodation Goes Both Ways: Studying Linguistic Convergence Between Humans and Language Models
di: Blevins, Terra
Pubblicazione: (2026)

Breaking the Script Barrier in Multilingual Pre-Trained Language Models with Transliteration-Based Post-Training Alignment
di: Xhelili, Orgest, et al.
Pubblicazione: (2024)

A Comprehensive Evaluation of Multilingual Chain-of-Thought Reasoning: Performance, Consistency, and Faithfulness Across Languages
di: Zhao, Raoyuan, et al.
Pubblicazione: (2025)

Why Better Cross-Lingual Alignment Fails for Better Cross-Lingual Transfer: Case of Encoders
di: Veitsman, Yana, et al.
Pubblicazione: (2026)

Left, Right, or Center? Evaluating LLM Framing in News Classification and Generation
di: Kennedy, Molly, et al.
Pubblicazione: (2026)

Influential Training Data Retrieval for Explaining Verbalized Confidence of LLMs
di: Xia, Yuxi, et al.
Pubblicazione: (2026)

HYPEROFA: Expanding LLM Vocabulary to New Languages via Hypernetwork-Based Embedding Initialization
di: Özeren, Enes, et al.
Pubblicazione: (2025)

TransliCo: A Contrastive Learning Framework to Address the Script Barrier in Multilingual Pretrained Language Models
di: Liu, Yihong, et al.
Pubblicazione: (2024)

TransMI: A Framework to Create Strong Baselines from Multilingual Pretrained Language Models for Transliterated Data
di: Liu, Yihong, et al.
Pubblicazione: (2024)

Parameter Alignment Mitigates Catastrophic Forgetting in Multilingual Expert Language Models
di: Ahuja, Sanchit, et al.
Pubblicazione: (2026)

Relational Linearity is a Predictor of Hallucinations
di: Lu, Yuetian, et al.
Pubblicazione: (2026)

Evaluating Robustness of Large Language Models Against Multilingual Typographical Errors
di: Zhao, Raoyuan, et al.
Pubblicazione: (2025)

How Programming Concepts and Neurons Are Shared in Code Language Models
di: Kargaran, Amir Hossein, et al.
Pubblicazione: (2025)

Your Pretrained Model Tells the Difficulty Itself: A Self-Adaptive Curriculum Learning Paradigm for Natural Language Understanding
di: Feng, Qi, et al.
Pubblicazione: (2025)

Exploring the Role of Transliteration in In-Context Learning for Low-resource Languages Written in Non-Latin Scripts
di: Ma, Chunlan, et al.
Pubblicazione: (2024)

Influence-driven Curriculum Learning for Pre-training on Limited Data
di: Schoenegger, Loris, et al.
Pubblicazione: (2025)

LangSAMP: Language-Script Aware Multilingual Pretraining
di: Liu, Yihong, et al.
Pubblicazione: (2024)

Refusal Direction is Universal Across Safety-Aligned Languages
di: Wang, Xinpeng, et al.
Pubblicazione: (2025)

OFA: A Framework of Initializing Unseen Subword Embeddings for Efficient Large-scale Multilingual Continued Pretraining
di: Liu, Yihong, et al.
Pubblicazione: (2023)

On the Entity-Level Alignment in Crosslingual Consistency
di: Liu, Yihong, et al.
Pubblicazione: (2025)

Understanding In-Context Machine Translation for Low-Resource Languages: A Case Study on Manchu
di: Pei, Renhao, et al.
Pubblicazione: (2025)

Shared Doubt: Zero-shot Cross-Lingual Confidence Estimation for Language Models
di: Kyriakou, Athina, et al.
Pubblicazione: (2026)

MoSECroT: Model Stitching with Static Word Embeddings for Crosslingual Zero-shot Transfer
di: Ye, Haotian, et al.
Pubblicazione: (2024)

Large Reasoning Models Are (Not Yet) Multilingual Latent Reasoners
di: Liu, Yihong, et al.
Pubblicazione: (2026)

Crosslingual On-Policy Self-Distillation for Multilingual Reasoning
di: Liu, Yihong, et al.
Pubblicazione: (2026)

Enhancing Robustness of Autoregressive Language Models against Orthographic Attacks via Pixel-based Approach
di: Yang, Han, et al.
Pubblicazione: (2025)

Demystifying Prompts in Language Models via Perplexity Estimation
di: Gonen, Hila, et al.
Pubblicazione: (2022)

GLUScope: A Tool for Analyzing GLU Neurons in Transformer Language Models
di: Gerstner, Sebastian, et al.
Pubblicazione: (2026)

An Evaluation of Explanation Methods for Black-Box Detectors of Machine-Generated Text
di: Schoenegger, Loris, et al.
Pubblicazione: (2024)

Mechanistic Understanding and Mitigation of Language Confusion in English-Centric Large Language Models
di: Nie, Ercong, et al.
Pubblicazione: (2025)

ReverseMath: Answer Inversion for Scalable and Verifiable Mathematical Problem Generation
di: Zhao, Raoyuan, et al.
Pubblicazione: (2026)

Lost in Multilinguality: Dissecting Cross-lingual Factual Inconsistency in Transformer Language Models
di: Wang, Mingyang, et al.
Pubblicazione: (2025)

Hybrid Human-LLM Corpus Construction and LLM Evaluation for Rare Linguistic Phenomena
di: Weissweiler, Leonie, et al.
Pubblicazione: (2024)

GKnow: Measuring the Entanglement of Gender Bias and Factual Gender
di: Veloso, Leonor, et al.
Pubblicazione: (2026)

Influences on LLM Calibration: A Study of Response Agreement, Loss Functions, and Prompt Styles
di: Xia, Yuxi, et al.
Pubblicazione: (2025)

Explaining Generalization of AI-Generated Text Detectors Through Linguistic Analysis
di: Xia, Yuxi, et al.
Pubblicazione: (2026)

SYNTHEVAL: Hybrid Behavioral Testing of NLP Models with Synthetic CheckLists
di: Zhao, Raoyuan, et al.
Pubblicazione: (2024)

Comparing Hallucination Detection Metrics for Multilingual Generation
di: Kang, Haoqiang, et al.
Pubblicazione: (2024)