Language Bias under Conflicting Information in Multilingual LLMs

• URL: http://arxiv.org/abs/2604.07123v1
• Date: Wed, 08 Apr 2026 14:18:26 GMT
• Title: Language Bias under Conflicting Information in Multilingual LLMs
• Abstract summary: Large Language Models (LLMs) have been shown to contain biases in the process of integrating conflicting information when answering questions.<n>Here we ask whether such biases also exist with respect to which language is used for each conflicting piece of information.<n>We find that all LLMs tested, including GPT-5.2, ignore the conflict and confidently assert only one of the possible answers in the large majority of cases.<n>There is a consistent bias across models in which languages are preferred, with a general bias against Russian and, for the longest context lengths, in favor of Chinese.
• Score: 0.17188280334580197
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) have been shown to contain biases in the process of integrating conflicting information when answering questions. Here we ask whether such biases also exist with respect to which language is used for each conflicting piece of information. To answer this question, we extend the conflicting needles in a haystack paradigm to a multilingual setting and perform a comprehensive set of evaluations with naturalistic news domain data in five different languages, for a range of multilingual LLMs of different sizes. We find that all LLMs tested, including GPT-5.2, ignore the conflict and confidently assert only one of the possible answers in the large majority of cases. Furthermore, there is a consistent bias across models in which languages are preferred, with a general bias against Russian and, for the longest context lengths, in favor of Chinese. Both of these patterns are consistent between models trained inside and outside of mainland China, though somewhat stronger in the former category.

Related papers

• Location Not Found: Exposing Implicit Local and Global Biases in Multilingual LLMs [35.2977350485249]
  This work aims to quantify models' inter- and intra-lingual biases, via their ability to answer locale-ambiguous questions.<n>We present LocQA, a test set containing 2,156 questions in 12 languages, referring to various locale-dependent facts such as laws, dates, and measurements.<n>We show a global bias towards answers relevant to the US-locale, even when models are asked in languages other than English.<n>In Intra-lingually, we show that when multiple locales are relevant for the same language, models act as demographic probability engines, prioritizing locales with larger populations.
  arXiv  Detail & Related papers  (2026-04-21T09:57:41Z)
• Cross-Language Bias Examination in Large Language Models [37.21579885190632]
  This study introduces an innovative multilingual bias evaluation framework for assessing bias in Large Language Models.<n>By translating the prompts and word list into five target languages, we compare different types of bias across languages.<n>For example, Arabic and Spanish consistently show higher levels of stereotype bias, while Chinese and English exhibit lower levels of bias.
  arXiv  Detail & Related papers  (2025-12-17T23:22:03Z)
• Linguistic Nepotism: Trading-off Quality for Language Preference in Multilingual RAG [55.258582772528506]
  We investigate whether the mixture of different document languages impacts generation and citation in unintended ways.<n>Across eight languages and six open-weight models, we find that models preferentially cite English sources when queries are in English.<n>We find that models sometimes trade-off document relevance for language preference, indicating that citation choices are not always driven by informativeness alone.
  arXiv  Detail & Related papers  (2025-09-17T12:58:18Z)
• Beyond Early-Token Bias: Model-Specific and Language-Specific Position Effects in Multilingual LLMs [50.07451351559251]
  We present a study across five typologically distinct languages (English, Russian, German, Hindi, and Vietnamese)<n>We examine how position bias interacts with prompt strategies and affects output entropy.
  arXiv  Detail & Related papers  (2025-05-22T02:23:00Z)
• 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)
• Do Multilingual Large Language Models Mitigate Stereotype Bias? [9.31741279000585]
  This study systematically trains six LLMs of identical size and architecture in English, German, French, Italian, and Spanish. We observe that multilingual models achieve not only lower bias but also superior prediction accuracy when compared to monolingual models.
  arXiv  Detail & Related papers  (2024-07-08T08:46:50Z)
• Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language Models [62.91524967852552]
  Large language models (LLMs) are typically multilingual due to pretraining on diverse multilingual corpora.<n>But can these models relate corresponding concepts across languages, i.e., be crosslingual?<n>This study evaluates state-of-the-art LLMs on inherently crosslingual tasks.
  arXiv  Detail & Related papers  (2024-06-23T15:15:17Z)
• CIF-Bench: A Chinese Instruction-Following Benchmark for Evaluating the Generalizability of Large Language Models [53.9835961434552]
  We introduce the Chinese Instruction-Following Benchmark (CIF-Bench) to evaluate the generalizability of large language models (LLMs) to the Chinese language. CIF-Bench comprises 150 tasks and 15,000 input-output pairs, developed by native speakers to test complex reasoning and Chinese cultural nuances. To mitigate data contamination, we release only half of the dataset publicly, with the remainder kept private, and introduce diversified instructions to minimize score variance.
  arXiv  Detail & Related papers  (2024-02-20T16:02:12Z)
• This Land is {Your, My} Land: Evaluating Geopolitical Biases in Language Models [40.61046400448044]
  We show that large language models (LLM) recall certain geographical knowledge inconsistently when queried in different languages. As a targeted case study, we consider territorial disputes, an inherently controversial and multilingual task. We propose a suite of evaluation metrics to precisely quantify bias and consistency in responses across different languages.
  arXiv  Detail & Related papers  (2023-05-24T01:16:17Z)
• Comparing Biases and the Impact of Multilingual Training across Multiple Languages [70.84047257764405]
  We present a bias analysis across Italian, Chinese, English, Hebrew, and Spanish on the downstream sentiment analysis task. We adapt existing sentiment bias templates in English to Italian, Chinese, Hebrew, and Spanish for four attributes: race, religion, nationality, and gender. Our results reveal similarities in bias expression such as favoritism of groups that are dominant in each language's culture.
  arXiv  Detail & Related papers  (2023-05-18T18:15:07Z)
• Gender Bias in Multilingual Embeddings and Cross-Lingual Transfer [101.58431011820755]
  We study gender bias in multilingual embeddings and how it affects transfer learning for NLP applications. We create a multilingual dataset for bias analysis and propose several ways for quantifying bias in multilingual representations.
  arXiv  Detail & Related papers  (2020-05-02T04:34:37Z)

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.