Camellia is a new benchmark that tests cultural bias in large language models (LLMs) across nine Asian languages and six Asian cultures. It contains 19,530 manually annotated entities linked to Asian or Western cultures and 2,173 masked social‑media contexts for these entities. Using Camellia, the authors evaluate four multilingual LLMs on cultural context adaptation, sentiment association, and entity extractive QA, finding that models struggle with cultural adaptation, exhibit differing biases across regions and families, and have difficulty understanding context in some Asian languages.
arXiv:2606. 01260v1 Announce Type: cross Abstract: Despite being home to more than 1300 ethnic groups and 700 indigenous languages, bias in Large Language Models has not been fully studied in Indonesia, thus leaving a critical gap in evaluating representational fairness and localized stereotypes within its uniquely vast, multilingual, and diverse sociocultural landscape.
The paper investigates cultural biases in large language models (LLMs) by introducing the Culture-Related Open Questions (CROQ) dataset, which contains 24‑language questions about generic culture. Experiments reveal that LLMs disproportionately favor Japan in their responses, especially when prompted in high‑resource languages, while low‑resource languages tend to highlight countries where the language is official. The study also finds that these biases emerge after supervised fine‑tuning rather than during pre‑training.
arXiv:2601. 14063v2 Announce Type: replace-cross Abstract: Cross-cultural competence in large language models (LLMs) requires understanding and adapting Culture-Specific Items (CSIs) across varying cultural contexts.
arXiv:2607. 20056v1 Announce Type: cross Abstract: Aspect-based sentiment analysis (ABSA) in Arabic must recover both explicitly stated aspects and implicit aspects that are never named in the text.
CoCoA (Context-Conditional Cultural Alignment) is a framework designed to mitigate cultural bias in large language models by learning context-conditional behavior. It trains on entity pairs under both culturally cued and neutral contexts, using a contrastive alignment objective combined with calibration, drift regularization, and goal-aware gradient reconciliation. Evaluations on CAMeL and Camellia across ten languages and four LLMs show that CoCoA reduces the Cultural Bias Score from 43 to 24 on average while keeping near-neutral preferences at 50.2, with minimal impact on general performance.
The study examines how multilingual large language models (LLMs) produce outputs that differ across sociocultural contexts, highlighting that identity labels and source-language cues can mislead assessments of cultural grounding. Using a human‑validated, multi‑agent audit on 89,253 outputs from 12 LLMs in English, French, and Chinese across 18 occupations and three task conditions, the authors find that bias representation varies systematically by language and task. Removing direct identity cues reduces identity‑label prediction in English and Chinese but not in French, and the source language’s cultural context consistently receives the highest relevance score, though this signal weakens after translation or name masking. "whyItMatters":"The findings show that surface cues can obscure true cross‑cultural patterns, underscoring the need for careful audit designs to avoid misleading conclusions about bias in multilingual LLMs."
arXiv:2607. 20241v1 Announce Type: cross Abstract: Culturally loaded translation poses unique challenges for machine translation (MT), as meanings are deeply embedded in socio-cultural contexts beyond surface linguistic forms.
arXiv:2608.28405v1 Announce Type: new Abstract: Current cultural evaluations for large language models (LLMs) often reduce culture to single-turn factual recall via MCQs, failing to capture a common...
arXiv:2607. 02235v1 Announce Type: cross Abstract: LLM-as-a-Judge has become the dominant evaluation paradigm for many natural language generation tasks, due to shortcomings of conventional metrics and high correlations with human judgment, albeit mostly in English.
arXiv:2608. 02486v1 Announce Type: cross Abstract: Open-source LLMs reliably name Zeus, Jupiter, and Thor, but recover their counterparts in less-represented traditions like Finnish, Slavic, Egyptian, or Chinese mythology far less consistently.
The paper investigates whether multilingual language models transfer factual knowledge from one language to another during continued pretraining. Using an English-pretrained model continued on Persian data with systematically removed facts, the authors create SIFT, a dataset of 500 triples across 20 relations, split by cultural origin. Their findings indicate that factual transfer is minimal, especially for Persian-related facts, and that simple removal strategies or easy negative candidate sets can overestimate transfer.
The paper investigates how to fairly compare language models across languages, noting that current evaluation methods vary widely and lack empirical validation. By training controlled monolingual models on parallel data and testing multilingual LLMs, the authors find that many normalized metrics suffer from biases due to tokenization, encoding, and orthographic differences. Instead, they recommend using sentence‑level negative log‑likelihood over semantically equivalent sequences for more reliable cross‑lingual comparisons.