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

arXiv: https://arxiv.org/abs/2609.04409 · HTML: https://mlsanity.com/paper/2609.04409/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 26 references that are in the map.
- First posted on arXiv 3 Sep 2026.

## Builds on (most cited first, 19 of 19)

- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model](https://mlsanity.com/paper/2402.07827/) (2024)
- [BLEnD: A Benchmark for LLMs on Everyday Knowledge in Diverse Cultures and Languages](https://mlsanity.com/paper/2406.09948/) (2024)
- [Multilingual LAMA: Investigating Knowledge in Multilingual Pretrained Language Models](https://mlsanity.com/paper/2102.00894/) (2021)
- [Cross-Lingual Consistency of Factual Knowledge in Multilingual Language Models](https://mlsanity.com/paper/2310.10378/) (2023)
- [X-FACTR: Multilingual Factual Knowledge Retrieval from Pretrained Language Models](https://mlsanity.com/paper/2010.06189/) (2020)
- [Still No Lie Detector for Language Models: Probing Empirical and Conceptual Roadblocks](https://mlsanity.com/paper/2307.00175/) (2023)
- [Aligning Large Language Models with Human Preferences through Representation Engineering](https://mlsanity.com/paper/2312.15997/) (2023)
- [MAPO: Advancing Multilingual Reasoning through Multilingual Alignment-as-Preference Optimization](https://mlsanity.com/paper/2401.06838/) (2024)
- [Common Sense Beyond English: Evaluating and Improving Multilingual Language Models for Commonsense Reasoning](https://mlsanity.com/paper/2106.06937/) (2021)
- [Lost in Multilinguality: Dissecting Cross-lingual Factual Inconsistency in Transformer Language Models](https://mlsanity.com/paper/2504.04264/) (2025)
- [Large Language Models as Markov Chains](https://mlsanity.com/paper/2410.02724/) (2024)
- [Adaptive Tool Use in Large Language Models with Meta-Cognition Trigger](https://mlsanity.com/paper/2502.12961/) (2025)
- [Language Imbalance Driven Rewarding for Multilingual Self-improving](https://mlsanity.com/paper/2410.08964/) (2024)
- [Bridging the Language Gaps in Large Language Models with Inference-Time Cross-Lingual Intervention](https://mlsanity.com/paper/2410.12462/) (2024)
- [Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline](https://mlsanity.com/paper/2505.20546/) (2025)
- [CALM: Unleashing the Cross-Lingual Self-Aligning Ability of Language Model Question Answering](https://mlsanity.com/paper/2501.18457/) (2025)
- [Post-Training Language Models for Crosslingual Consistency](https://mlsanity.com/paper/2603.04678/) (2026)

## Abstract (arXiv)

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.