Rethinking Cross-lingual Gaps from a Statistical Viewpoint

• URL: http://arxiv.org/abs/2510.15551v1
• Date: Fri, 17 Oct 2025 11:34:04 GMT
• Title: Rethinking Cross-lingual Gaps from a Statistical Viewpoint
• Authors: Vihari Piratla, Purvam Jain, Darshan Singh, Partha Talukdar, Trevor Cohn,
• Abstract summary: Large Language Models (LLMs) act as a bridge by acquiring knowledge from a source language and making it accessible when queried from target languages.<n>Prior research has pointed to a cross-lingual gap, viz., a drop in accuracy when the knowledge is queried in a target language compared to when the query is in the source language.<n>We take an alternative view and hypothesize that the variance of responses in the target language is the main cause of this gap.
• Score: 24.938886584535926
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Any piece of knowledge is usually expressed in one or a handful of natural languages on the web or in any large corpus. Large Language Models (LLMs) act as a bridge by acquiring knowledge from a source language and making it accessible when queried from target languages. Prior research has pointed to a cross-lingual gap, viz., a drop in accuracy when the knowledge is queried in a target language compared to when the query is in the source language. Existing research has rationalized divergence in latent representations in source and target languages as the source of cross-lingual gap. In this work, we take an alternative view and hypothesize that the variance of responses in the target language is the main cause of this gap. For the first time, we formalize the cross-lingual gap in terms of bias-variance decomposition. We present extensive experimental evidence which support proposed formulation and hypothesis. We then reinforce our hypothesis through multiple inference-time interventions that control the variance and reduce the cross-lingual gap. We demonstrate a simple prompt instruction to reduce the response variance, which improved target accuracy by 20-25% across different models.

Related papers

• When Meanings Meet: Investigating the Emergence and Quality of Shared Concept Spaces during Multilingual Language Model Training [57.230355403478995]
  We investigate the development of language-agnostic concept spaces during pretraining of EuroLLM.<n>We find that shared concept spaces emerge early and continue to refine, but that alignment with them is language-dependent.<n>In contrast to prior work, our fine-grained manual analysis reveals that some apparent gains in translation quality reflect shifts in behavior.
  arXiv  Detail & Related papers  (2026-01-30T11:23:01Z)
• Align to the Pivot: Dual Alignment with Self-Feedback for Multilingual Math Reasoning [71.4175109189942]
  We present Pivot-Aligned Self-Feedback Multilingual Reasoning (PASMR)<n>This approach designates the model's primary language as the pivot language.<n>It establishes a cross-lingual self-feedback mechanism without relying on external correct answers or reward models.
  arXiv  Detail & Related papers  (2026-01-25T03:20:00Z)
• Why Do Multilingual Reasoning Gaps Emerge in Reasoning Language Models? [18.99223776816893]
  Reasoning language models (RLMs) achieve strong performance on complex reasoning tasks, yet they still suffer from a multilingual reasoning gap.<n>This paper shows that the multilingual reasoning gap largely stems from failures in language understanding.<n>We propose Selective Translation, a simple yet effective strategy that translates the multilingual input into English only when an understanding failure is detected.
  arXiv  Detail & Related papers  (2025-10-31T08:17:59Z)
• Assessing Agentic Large Language Models in Multilingual National Bias [31.67058518564021]
  Cross-language disparities in reasoning-based recommendations remain largely unexplored.<n>This study is the first to address this gap.<n>We investigate multilingual bias in state-of-the-art LLMs by analyzing their responses to decision-making tasks across multiple languages.
  arXiv  Detail & Related papers  (2025-02-25T08:07:42Z)
• Zero-shot Cross-lingual Stance Detection via Adversarial Language Adaptation [7.242609314791262]
  This paper introduces a novel approach to zero-shot cross-lingual stance detection, Multilingual Translation-Augmented BERT (MTAB) Our technique employs translation augmentation to improve zero-shot performance and pairs it with adversarial learning to further boost model efficacy. We demonstrate the effectiveness of our proposed approach, showcasing improved results in comparison to a strong baseline model as well as ablated versions of our model.
  arXiv  Detail & Related papers  (2024-04-22T16:56:43Z)
• Measuring Cross-lingual Transfer in Bytes [9.011910726620538]
  We show that models from diverse languages perform similarly to a target language in a cross-lingual setting. We also found evidence that this transfer is not related to language contamination or language proximity. Our experiments have opened up new possibilities for measuring how much data represents the language-agnostic representations learned during pretraining.
  arXiv  Detail & Related papers  (2024-04-12T01:44:46Z)
• Lost in Translation -- Multilingual Misinformation and its Evolution [52.07628580627591]
  This paper investigates the prevalence and dynamics of multilingual misinformation through an analysis of over 250,000 unique fact-checks spanning 95 languages. We find that while the majority of misinformation claims are only fact-checked once, 11.7%, corresponding to more than 21,000 claims, are checked multiple times. Using fact-checks as a proxy for the spread of misinformation, we find 33% of repeated claims cross linguistic boundaries.
  arXiv  Detail & Related papers  (2023-10-27T12:21:55Z)
• Quantifying the Dialect Gap and its Correlates Across Languages [69.18461982439031]
  This work will lay the foundation for furthering the field of dialectal NLP by laying out evident disparities and identifying possible pathways for addressing them through mindful data collection.
  arXiv  Detail & Related papers  (2023-10-23T17:42:01Z)
• Delving Deeper into Cross-lingual Visual Question Answering [115.16614806717341]
  We show that simple modifications to the standard training setup can substantially reduce the transfer gap to monolingual English performance. We analyze cross-lingual VQA across different question types of varying complexity for different multilingual multimodal Transformers.
  arXiv  Detail & Related papers  (2022-02-15T18:22:18Z)
• AM2iCo: Evaluating Word Meaning in Context across Low-ResourceLanguages with Adversarial Examples [51.048234591165155]
  We present AM2iCo, Adversarial and Multilingual Meaning in Context. It aims to faithfully assess the ability of state-of-the-art (SotA) representation models to understand the identity of word meaning in cross-lingual contexts. Results reveal that current SotA pretrained encoders substantially lag behind human performance.
  arXiv  Detail & Related papers  (2021-04-17T20:23:45Z)
• Counterfactual VQA: A Cause-Effect Look at Language Bias [117.84189187160005]
  VQA models tend to rely on language bias as a shortcut and fail to sufficiently learn the multi-modal knowledge from both vision and language. We propose a novel counterfactual inference framework, which enables us to capture the language bias as the direct causal effect of questions on answers.
  arXiv  Detail & Related papers  (2020-06-08T01:49:27Z)

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.