A Systematic Evaluation of Cross-Lingual Consistency Enhancement Methods in Multilingual Language Models

• URL: http://arxiv.org/abs/2609.04409v1
• Date: Thu, 03 Sep 2026 19:18:44 GMT
• Title: A Systematic Evaluation of Cross-Lingual Consistency Enhancement Methods in Multilingual Language Models
• Abstract summary: We present a unified evaluation of representative CLC-enhancement methods for question answering, spanning inference-time interventions and post-training approaches.<n>Results show that post-training methods are generally more reliable, with direct distribution alignment consistently improving CLC across all model-dataset combinations.<n>We investigate whether CLC enhancement hurts models' ability to respond differently *when needed*, that is, when asked culture-dependent questions.
• Score: 50.27606276000142
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multilingual language models often produce inconsistent answers to semantically equivalent questions across languages, motivating methods to improve cross-lingual consistency (CLC). However, existing methods are typically evaluated using different models, tasks, and protocols, leaving their relative strengths unclear. In this work, we present a unified evaluation of representative CLC-enhancement methods for question answering, spanning inference-time interventions and post-training approaches across three model families and three closed-form benchmarks. The results show that post-training methods are generally more reliable, with direct distribution alignment consistently improving CLC across all model-dataset combinations, while other methods are more sensitive to answer format and the breadth of language coverage. Notably, cross-domain transfer is limited unless source and target tasks share similar output formats. We further investigate whether CLC enhancement hurts models' ability to respond differently *when needed*, that is, when asked culture-dependent questions. Across two benchmarks of culturally diverse question answering, we find no systematic degradation in controlled closed-form evaluation, whereas open-ended generation reveals occasional accuracy reductions, particularly for non-English responses. Our work highlights the need to evaluate CLC enhancement for both cross-domain robustness and culturally appropriate variation, informing future work in post-training and benchmark development.

Related papers

• Inference-Time Steering for Cross-Lingual Factual Consistency in LLMs [51.56484100374058]
  Large Language Models (LLMs) demonstrate remarkable multilingual fluency, but their internal knowledge representations remain disproportionately biased toward high-resource languages.<n>We investigate whether these biases can be mitigated at inference time, forcing an English-prompted model to answer as if it were queried in target languages.<n>Experiments on Gemma 3 12B Instruct reveal persona prompting to be the strongest overall intervention, balancing efficacy, safety, and out-of-domain generalization.
  arXiv  Detail & Related papers  (2026-07-21T16:15:05Z)
• Optimizing Language Models for Crosslingual Knowledge Consistency [90.86445137816942]
  Large language models are known to often exhibit inconsistent knowledge.<n>This is particularly problematic in multilingual scenarios, where models are likely to be asked similar questions in different languages.<n>In this work, we show that this issue can be mitigated using reinforcement learning with a structured reward function.
  arXiv  Detail & Related papers  (2026-03-04T23:36:55Z)
• CM-Align: Consistency-based Multilingual Alignment for Large Language Models [84.19366314925593]
  We propose a consistency-based data method to construct high-quality multilingual preference data.<n> Specifically, our method includes two parts: consistency-guided English reference selection and cross-lingual consistency-based multilingual preference data construction.
  arXiv  Detail & Related papers  (2025-09-10T12:40:49Z)
• Cross-Lingual Pitfalls: Automatic Probing Cross-Lingual Weakness of Multilingual Large Language Models [55.14276067678253]
  This paper introduces a novel methodology for efficiently identifying inherent cross-lingual weaknesses in Large Language Models (LLMs)<n>We construct a new dataset of over 6,000 bilingual pairs across 16 languages using this methodology, demonstrating its effectiveness in revealing weaknesses even in state-of-the-art models.<n>Further experiments investigate the relationship between linguistic similarity and cross-lingual weaknesses, revealing that linguistically related languages share similar performance patterns.
  arXiv  Detail & Related papers  (2025-05-24T12:31:27Z)
• CALM: Unleashing the Cross-Lingual Self-Aligning Ability of Language Model Question Answering [42.92810049636768]
  Large Language Models (LLMs) are pretrained on extensive multilingual corpora to acquire both language-specific cultural knowledge and general knowledge.<n>We explore the Cross-Lingual Self-Aligning ability of Language Models (CALM) to align knowledge across languages.<n>We employ direct preference optimization (DPO) to align the model's knowledge across different languages.
  arXiv  Detail & Related papers  (2025-01-30T16:15:38Z)
• Align, Generate, Learn: A Novel Closed-Loop Framework for Cross-Lingual In-Context Learning [0.0]
  Cross-lingual in-context learning (XICL) has emerged as a transformative paradigm for leveraging large language models (LLMs) to tackle multilingual tasks.<n>We propose a novel self-supervised framework that harnesses the generative capabilities of LLMs to internally select and utilize task-relevant examples.
  arXiv  Detail & Related papers  (2024-12-12T05:36:51Z)
• ConVerSum: A Contrastive Learning-based Approach for Data-Scarce Solution of Cross-Lingual Summarization Beyond Direct Equivalents [4.029675201787349]
  Cross-lingual summarization is a sophisticated branch in Natural Language Processing. There is no feasible solution for CLS when there is no available high-quality CLS data. We propose a novel data-efficient approach, ConVerSum, for CLS leveraging the power of contrastive learning.
  arXiv  Detail & Related papers  (2024-08-17T19:03:53Z)
• Evaluating Knowledge-based Cross-lingual Inconsistency in Large Language Models [16.942897938964638]
  Large Language Models (LLMs) have shown exceptional performance in various Natural Language Processing (NLP) tasks. Despite their successes, these models often exhibit significant inconsistencies when processing the same concepts across different languages. This study focuses on three primary questions: the existence of cross-lingual inconsistencies in LLMs, the specific aspects in which these inconsistencies manifest, and the correlation between cross-lingual consistency and multilingual capabilities of LLMs.
  arXiv  Detail & Related papers  (2024-07-01T15:11:37Z)
• Improving the Consistency in Cross-Lingual Cross-Modal Retrieval with 1-to-K Contrastive Learning [23.54908503106691]
  Cross-lingual Cross-modal Retrieval ( CCR) is an essential task in web search. We propose a new 1-to-K contrastive learning method, which treats each language equally. Our method improves both recall rates and Mean Rank Variance (MRV) with smaller-scale pre-trained data.
  arXiv  Detail & Related papers  (2024-06-26T11:04:25Z)
• 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)
• Cross-lingual QA: A Key to Unlocking In-context Cross-lingual Performance [2.371686365695081]
  Cross-lingual QA is a cross-lingual prompting method that translates only the question and answer parts, thus reducing translation costs. Experiments on four typologically diverse multilingual benchmarks show that Cross-lingual QA effectively stimulates models to elicit their cross-lingual knowledge. We show that prompting open-source MLLMs with cross-lingual in-context examples enhances performance as the model scale increases.
  arXiv  Detail & Related papers  (2023-05-24T15:14:49Z)

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.