Cross-Lingual Consistency in Language Models

Follow this topic Ask about this topic

This field asks whether language models preserve answers, reasoning, and safety behavior when the same meaning is expressed in different languages, scripts, or dialects. Researchers use parallel question-answering, factual-recall, reasoning, and safety benchmarks, measuring both accuracy and agreement across language versions. Methods include multilingual fine-tuning and reinforcement learning, representation alignment, preference optimization, and inference-time steering. Results show persistent gaps, especially for lower-resource languages, while leaving an important tension: models should be consistent on shared facts and safety rules without erasing culturally appropriate differences.

Latest papers

72 papers14 papers in the last four weeks, level with the four weeks before. 0.1% of all new papers.

Mitigating Cross-Lingual Cultural Inconsistencies in LLMs via Consensus-Driven Preference Optimisation
Apr 2, 2026Lucas Resck, Isabelle Augenstein, Anna KorhonenCross-Lingual Consistency in Language Models Cross-Cultural Language Model Evaluation
Language Technology Lab, University of Cambridge · University of Copenhagen
Structured Intent as a Protocol-Like Communication Layer: Cross-Model Robustness, Framework Comparison, and the Weak-Model Compensation Effect
Mar 31, 2026Peng GangStructured Prompting Human-AI Interaction
Huizhou Lateni AI Technology Co., Ltd., Huizhou, China · Huizhou University, Huizhou, China
Does Structured Intent Representation Generalize? A Cross-Language, Cross-Model Empirical Study of 5W3H Prompting
Mar 26, 2026Peng GangStructured Prompting LLM Prompting
Huizhou Lateni AI Technology Co., Ltd., Huizhou, China · Huizhou University, Huizhou, China
Imperative Interference: Social Register Shapes Instruction Topology in Large Language Models
Mar 26, 2026Tony MasonPragmatic Reasoning in Language Models Cross-Lingual Consistency in Language Models
the University of British Columbia · the Georgia Institute of Technology
IndicSafe: A Benchmark for Evaluating Multilingual LLM Safety in South Asia
Mar 18, 2026Priyaranjan Pattnayak, Sanchari ChowdhuriLanguage Model Safety Evaluation LLM Safety Benchmarks
Oracle America Inc.
Language Shapes Mental Health Evaluations in Large Language Models
Mar 6, 2026Jiayi Xu, Xiyang HuCross-Lingual Consistency in Language Models Multilingual Language Model Evaluation
University of North Carolina at Chapel Hill · Arizona State University
Alignment Backfire: Language-Dependent Reversal of Safety Interventions Across 16 Languages in LLM Multi-Agent Systems
Mar 5, 2026Hiroki FukuiLLM Safety LLM Alignment
Research Institute of Criminal Psychiatry / Sex Offender Medical Center; Department of Neuropsychiatry, Kyoto University
Post-Training Language Models for Crosslingual Consistency
Mar 4, 2026Tianyu Liu, Jirui Qi, Mrinmaya Sachan +3Cross-Lingual Consistency in Language Models Language Model Post-Training
ETH Zürich · CLCG, University of Groningen · University of Amsterdam
Universal Conceptual Structure in Neural Translation: Probing NLLB-200's Multilingual Geometry
Feb 27, 2026Kyle Elliott MathewsonMultilingual Language Models Representation Geometry in Language Models
University of Alberta
Cross-Lingual Sentiment Misalignment: Auditing Multilingual Language Models for Inversion Risk, Dialectal Representation, and Affective Stability
Feb 19, 2026Nusrat Jahan Lia, Shubhashis Roy DiptaDialect Bias in Language Models Cross-Lingual Consistency in Language Models
Institute of Information Technology, University of Dhaka, Dhaka, Bangladesh · University of Maryland, Baltimore County, Baltimore, Maryland, USA
Align Once, Benefit Multilingually: Enforcing Multilingual Consistency for LLM Safety Alignment
Feb 18, 2026Yuyan Bu, Xiaohao Liu, ZhaoXing Ren +2LLM Safety Alignment Cross-Lingual Consistency in Language Models
Beijing Academy of Artificial Intelligence · National University of Singapore · Institute for Artificial Intelligence, Peking University
One Model, Many Morals: Uncovering Cross-Linguistic Misalignments in Computational Moral Reasoning
Sep 25, 2025Sualeha Farid, Jayden Lin, Zean Chen +2Multilingual Language Model Evaluation Moral Reasoning in Language Models
University of Michigan, Ann Arbor, USA

Apr 2, 2026J/K move · Enter open · S save

Mitigating Cross-Lingual Cultural Inconsistencies in LLMs via Consensus-Driven Preference Optimisation

Lucas Resck, Isabelle Augenstein, Anna Korhonen

Language Technology Lab, University of Cambridge · University of Copenhagen

Cross-Lingual Consistency in Language Models Cross-Cultural Language Model Evaluation Preference Optimization Personalized Language Model Alignment

Open paper AskPDF arXiv

Multilingual large language models (MLLMs) often answer culturally ambiguous questions inconsistently across languages, even for a fixed user persona -- e.g., Shakespeare in English but Cervantes in Spanish for the same British user. To robustly quantify this Cross-lingual Cultural Inconsistency, we introduce Singleton Fleiss's

κ_S

, a metric mathematically resilient to hallucinations. For mitigation, we propose Cross-lingual Cultural Consistent Preference Optimisation (C-3PO), a consensus-driven alignment framework. C-3PO raises

κ_S

by 0.07--0.10 over unaligned models, above every prompting and representation steering baseline averaged across personas, whilst largely preserving explicit user identities, cultural neutrality and intrinsic cultural knowledge; where it does not, a soft-consensus variant recovers most of the cost. Although trained only on multiple-choice questions, C-3PO also improves consistency in open-ended generation. Empirical evaluations demonstrate this inconsistency is more pronounced for lower-resource languages like Indonesian and Persian. Finally, early decoding of intermediate layers reveals that MLLMs implicitly personalise outputs towards the prompt language's stereotypical culture as forward-pass representations stabilise.