相关论文: CulturALL: Benchmarking Multilingual and Multicult…

Existing Large Multimodal Models (LMMs) generally focus on only a few regions and languages. As LMMs continue to improve, it is increasingly important to ensure they understand cultural contexts, respect local sensitivities, and support…

Large language models (LLMs) are now used worldwide, yet their multimodal understanding and reasoning often degrade outside Western, high-resource settings. We propose MMA-ASIA, a comprehensive framework to evaluate LLMs' cultural awareness…

Large language models (LLMs) are increasingly deployed as autonomous agents, yet evaluations focus primarily on task success rather than cultural appropriateness or evaluator reliability. We introduce LiveCultureBench, a multi-cultural,…

Cultural competence, defined as the ability to understand and adapt to multicultural contexts, is increasingly vital for large language models (LLMs) in global environments. While several cultural benchmarks exist to assess LLMs' cultural…

Existing benchmarks that measure cultural adaptation in LLMs are misaligned with the actual challenges these models face when interacting with users from diverse cultural backgrounds. In this work, we introduce the first framework and…

Vision-language models (VLMs) have advanced human-AI interaction but struggle with cultural understanding, often misinterpreting symbols, gestures, and artifacts due to biases in predominantly Western-centric training data. In this paper,…

The performance differential of large language models (LLM) between languages hinders their effective deployment in many regions, inhibiting the potential economic and societal value of generative AI tools in many communities. However, the…

Large language models exhibit cultural biases and limited cross-cultural understanding capabilities, particularly when serving diverse global user populations. We propose MCEval, a novel multilingual evaluation framework that employs…

Large language models (LLMs) have demonstrated substantial commonsense understanding through numerous benchmark evaluations. However, their understanding of cultural commonsense remains largely unexamined. In this paper, we conduct a…

As the scaling of Large Language Models (LLMs) has dramatically enhanced their capabilities, there has been a growing focus on the alignment problem to ensure their responsible and ethical use. While existing alignment efforts predominantly…

Recent advancements in large language models (LLMs) showcase varied multilingual capabilities across tasks like translation, code generation, and reasoning. Previous assessments often limited their scope to fundamental natural language…

The breakthrough of generative large language models (LLMs) that can solve different tasks through chat interaction has led to a significant increase in the use of general benchmarks to assess the quality or performance of these models…

Frontier large language models (LLMs) are developed by researchers and practitioners with skewed cultural backgrounds and on datasets with skewed sources. However, LLMs' (lack of) multicultural knowledge cannot be effectively assessed with…

Large language models (LLMs) often lack culture-specific knowledge of daily life, especially across diverse regions and non-English languages. Existing benchmarks for evaluating LLMs' cultural sensitivities are limited to a single language…

Large-scale deployment of large language models (LLMs) in various applications, such as chatbots and virtual assistants, requires LLMs to be culturally sensitive to the user to ensure inclusivity. Culture has been widely studied in…

Evaluating the multilingual and multicultural capabilities of Large Language Models (LLMs) is essential for their global utility. However, current benchmarks face three critical limitations: (1) fragmented evaluation dimensions that often…

Multimodal language analysis is a rapidly evolving field that leverages multiple modalities to enhance the understanding of high-level semantics underlying human conversational utterances. Despite its significance, little research has…

Large language models (LLMs) are reported to be partial to certain cultures owing to the training data dominance from the English corpora. Since multilingual cultural data are often expensive to collect, existing efforts handle this by…

As large language models (LLMs) are employed worldwide, existing evaluation paradigms for their multilingual capabilities primarily focus on factual task performance, neglecting the ability to judge content's deep-level values across…

As the capabilities of large language models (LLMs) continue to advance, evaluating their performance becomes increasingly crucial and challenging. This paper aims to bridge this gap by introducing CMMLU, a comprehensive Chinese benchmark…