{"total":71,"rows":[{"id":"2403.15412","title":"Towards Measuring and Modeling \"Culture\" in LLMs: A Survey","created":"2024-03-05","cited_by_count":167,"area":null},{"id":"2406.16020","title":"AudioBench: A Universal Benchmark for Audio Large Language Models","created":"2024-06-23","cited_by_count":128,"area":null},{"id":"2406.05761","title":"The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models","created":"2024-06-09","cited_by_count":93,"area":null},{"id":"2406.10118","title":"SEACrowd: A Multilingual Multimodal Data Hub and Benchmark Suite for Southeast Asian Languages","created":"2024-06-14","cited_by_count":43,"area":null},{"id":"2502.12057","title":"Culture is Not Trivia: Sociocultural Theory for Cultural NLP","created":"2025-02-17","cited_by_count":40,"area":null},{"id":"2310.10570","title":"On Context Utilization in Summarization with Large Language Models","created":"2023-10-16","cited_by_count":30,"area":null},{"id":"2404.04659","title":"Multilingual Pretraining and Instruction Tuning Improve Cross-Lingual Knowledge Alignment, But Only Shallowly","created":"2024-04-06","cited_by_count":27,"area":null},{"id":"2411.02460","title":"Code-Switching Curriculum Learning for Multilingual Transfer in LLMs","created":"2024-11-04","cited_by_count":27,"area":null},{"id":"2406.03930","title":"Culturally Aware and Adapted NLP: A Taxonomy and a Survey of the State of the Art","created":"2024-06-06","cited_by_count":26,"area":null},{"id":"2406.11565","title":"Extrinsic Evaluation of Cultural Competence in Large Language Models","created":"2024-06-17","cited_by_count":24,"area":null},{"id":"2410.12462","title":"Bridging the Language Gaps in Large Language Models with Inference-Time Cross-Lingual Intervention","created":"2024-10-16","cited_by_count":24,"area":null},{"id":"2406.07302","title":"BertaQA: How Much Do Language Models Know About Local Culture?","created":"2024-06-11","cited_by_count":23,"area":null},{"id":"2502.07346","title":"BenchMAX: A Comprehensive Multilingual Evaluation Suite for Large Language Models","created":"2025-02-11","cited_by_count":23,"area":null},{"id":"2406.11661","title":"Cultural Conditioning or Placebo? On the Effectiveness of Socio-Demographic Prompting","created":"2024-06-17","cited_by_count":22,"area":null},{"id":"2504.05747","title":"SEA-LION: Southeast Asian Languages in One Network","created":"2025-04-08","cited_by_count":22,"area":null},{"id":"2404.09754","title":"Resilience of Large Language Models for Noisy Instructions","created":"2024-04-15","cited_by_count":20,"area":null},{"id":"2407.16222","title":"PreAlign: Boosting Cross-Lingual Transfer by Early Establishment of Multilingual Alignment","created":"2024-07-23","cited_by_count":20,"area":null},{"id":"2502.14301","title":"SEA-HELM: Southeast Asian Holistic Evaluation of Language Models","created":"2025-02-20","cited_by_count":19,"area":null},{"id":"2502.12982","title":"Sailor2: Sailing in South-East Asia with Inclusive Multilingual LLMs","created":"2025-02-18","cited_by_count":18,"area":null},{"id":"2405.13974","title":"CIVICS: Building a Dataset for Examining Culturally-Informed Values in Large Language Models","created":"2024-05-22","cited_by_count":16,"area":null},{"id":"2407.20750","title":"JaColBERTv2.5: Optimising Multi-Vector Retrievers to Create State-of-the-Art Japanese Retrievers with Constrained Resources","created":"2024-07-30","cited_by_count":15,"area":null},{"id":"2406.15948","title":"Teaching LLMs to Abstain across Languages via Multilingual Feedback","created":"2024-06-22","cited_by_count":14,"area":null},{"id":"2502.06298","title":"SeaExam and SeaBench: Benchmarking LLMs with Local Multilingual Questions in Southeast Asia","created":"2025-02-10","cited_by_count":13,"area":null},{"id":"2509.19274","title":"DRISHTIKON: A Multimodal Multilingual Benchmark for Testing Language Models' Understanding on Indian Culture","created":"2025-09-23","cited_by_count":13,"area":null},{"id":"2509.16188","title":"CultureScope: A Dimensional Lens for Probing Cultural Understanding in LLMs","created":"2025-09-19","cited_by_count":12,"area":null},{"id":"2404.11932","title":"CrossIn: An Efficient Instruction Tuning Approach for Cross-Lingual Knowledge Alignment","created":"2024-04-18","cited_by_count":11,"area":null},{"id":"2511.17282","title":"Where Culture Fades: Revealing the Cultural Gap in Text-to-Image Generation","created":"2025-11-21","cited_by_count":11,"area":null},{"id":"2408.03560","title":"In2Core: Leveraging Influence Functions for Coreset Selection in Instruction Finetuning of Large Language Models","created":"2024-08-07","cited_by_count":9,"area":null},{"id":"2502.11020","title":"TUMLU: A Unified and Native Language Understanding Benchmark for Turkic Languages","created":"2025-02-16","cited_by_count":9,"area":null},{"id":"2507.14239","title":"CCL-XCoT: An Efficient Cross-Lingual Knowledge Transfer Method for Mitigating Hallucination Generation","created":"2025-07-17","cited_by_count":9,"area":null},{"id":"2405.03138","title":"CRAFT: Extracting and Tuning Cultural Instructions from the Wild","created":"2024-05-06","cited_by_count":8,"area":null},{"id":"2508.16431","title":"Cetvel: A Unified Benchmark for Evaluating Language Understanding, Generation and Cultural Capacity of LLMs for Turkish","created":"2025-08-22","cited_by_count":8,"area":null},{"id":"2505.19776","title":"Analyzing Political Bias in LLMs via Target-Oriented Sentiment Classification","created":"2025-05-26","cited_by_count":7,"area":null},{"id":"2502.09387","title":"Truth Knows No Language: Evaluating Truthfulness Beyond English","created":"2025-02-13","cited_by_count":5,"area":null},{"id":"2502.14911","title":"Batayan: A Filipino NLP benchmark for evaluating Large Language Models","created":"2025-02-19","cited_by_count":5,"area":null},{"id":"2503.01150","title":"MiLiC-Eval: Benchmarking Multilingual LLMs for China's Minority Languages","created":"2025-03-03","cited_by_count":5,"area":null},{"id":"2507.12838","title":"Are Knowledge and Reference in Multilingual Language Models Cross-Lingually Consistent?","created":"2025-07-17","cited_by_count":5,"area":null},{"id":"2510.08608","title":"MMA-ASIA: A Multilingual and Multimodal Alignment Framework for Culturally-Grounded Evaluation","created":"2025-10-07","cited_by_count":5,"area":null},{"id":"2406.14434","title":"Selected Languages are All You Need for Cross-lingual Truthfulness Transfer","created":"2024-06-20","cited_by_count":4,"area":null},{"id":"2410.19419","title":"KAHANI: Culturally-Nuanced Visual Storytelling Tool for Non-Western Cultures","created":"2024-10-25","cited_by_count":4,"area":null},{"id":"2411.05253","title":"What talking you?: Translating Code-Mixed Messaging Texts to English","created":"2024-11-08","cited_by_count":4,"area":null},{"id":"2501.08335","title":"MERaLiON-TextLLM: Cross-Lingual Understanding of Large Language Models in Chinese, Indonesian, Malay, and Singlish","created":"2024-12-21","cited_by_count":4,"area":null},{"id":"2504.10906","title":"Understanding LLMs' Cross-Lingual Context Retrieval: How Good It Is And Where It Comes From","created":"2025-04-15","cited_by_count":4,"area":null},{"id":"2508.02241","title":"Isolating Culture Neurons in Multilingual Large Language Models","created":"2025-08-04","cited_by_count":4,"area":null},{"id":"2312.16144","title":"Towards Better Monolingual Japanese Retrievers with Multi-Vector Models","created":"2023-12-26","cited_by_count":3,"area":null},{"id":"2409.15380","title":"Kalahi: A handcrafted, grassroots cultural LLM evaluation suite for Filipino","created":"2024-09-20","cited_by_count":3,"area":null},{"id":"2411.04794","title":"KnowCoder-X: Boosting Multilingual Information Extraction via Code","created":"2024-11-07","cited_by_count":3,"area":null},{"id":"2412.01186","title":"SailCompass: Towards Reproducible and Robust Evaluation for Southeast Asian Languages","created":"2024-12-02","cited_by_count":3,"area":null},{"id":"2505.19116","title":"Controlling Language Confusion in Multilingual LLMs","created":"2025-05-25","cited_by_count":3,"area":null},{"id":"2506.00482","title":"Benchmarks Are Not Atomic: Composition-Aware LLM Evaluation using BenchHub","created":"2025-05-31","cited_by_count":3,"area":null},{"id":"2507.09701","title":"MCEval: A Dynamic Framework for Fair Multilingual Cultural Evaluation of LLMs","created":"2025-07-13","cited_by_count":3,"area":null},{"id":"2310.10981","title":"Instructive Dialogue Summarization with Query Aggregations","created":"2023-10-17","cited_by_count":2,"area":null},{"id":"2411.04637","title":"Hands-On Tutorial: Labeling with LLM and Human-in-the-Loop","created":"2024-11-07","cited_by_count":2,"area":null},{"id":"2506.02412","title":"SingaKids: A Multilingual Multimodal Dialogic Tutor for Language Learning","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2506.03619","title":"Do Large Language Models Know Folktales? A Case Study of Yokai in Japanese Folktales","created":"2025-06-04","cited_by_count":2,"area":null},{"id":"2511.11334","title":"LaoBench: A Large-Scale Multidimensional Lao Benchmark for Large Language Models","created":"2025-11-14","cited_by_count":2,"area":null},{"id":"2503.04064","title":"Uncovering inequalities in new knowledge learning by large language models across different languages","created":"2025-03-06","cited_by_count":1,"area":null},{"id":"2505.02177","title":"Measuring Hong Kong Massive Multi-Task Language Understanding","created":"2025-05-04","cited_by_count":1,"area":null},{"id":"2602.18788","title":"BURMESE-SAN: Burmese NLP Benchmark for Evaluating Large Language Models","created":"2026-02-21","cited_by_count":1,"area":null},{"id":"2604.19262","title":"CulturALL: Benchmarking Multilingual and Multicultural Competence of LLMs on Grounded Tasks","created":"2026-04-21","cited_by_count":1,"area":null},{"id":"2310.16528","title":"CUNI Submission to MRL 2023 Shared Task on Multi-lingual Multi-task Information Retrieval","created":"2023-10-25","cited_by_count":0,"area":null},{"id":"2311.04495","title":"Multi-label and Multi-target Sampling of Machine Annotation for Computational Stance Detection","created":"2023-11-08","cited_by_count":0,"area":null},{"id":"2409.16849","title":"Exposing Assumptions in AI Benchmarks through Cognitive Modelling","created":"2024-09-25","cited_by_count":0,"area":null},{"id":"2410.16156","title":"Limpeh ga li gong: Challenges in Singlish Annotations","created":"2024-10-21","cited_by_count":0,"area":null},{"id":"2508.05468","title":"TASE: Token Awareness and Structured Evaluation for Multilingual Language Models","created":"2025-08-07","cited_by_count":0,"area":null},{"id":"2602.17283","title":"Towards Cross-lingual Values Judgment: A Consensus-Pluralism Perspective","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2603.16406","title":"Who Benchmarks the Benchmarks? A Case Study of LLM Evaluation in Icelandic","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2603.17303","title":"From Words to Worlds: Benchmarking Cross-Cultural Cultural Understanding in Machine Translation","created":"2026-03-18","cited_by_count":0,"area":null},{"id":"2604.13058","title":"KMMMU: Evaluation of Massive Multi-discipline Multimodal Understanding in Korean Language and Context","created":"2026-03-18","cited_by_count":0,"area":null},{"id":"2608.21853","title":"PUMA: A Polish Benchmark for Culturally Grounded Multimodal Understanding","created":"2026-08-22","cited_by_count":0,"area":null},{"id":"2609.22494","title":"CultureMINE: Datasets and Methods for Improving the Cultural Capabilities of NLP Systems","created":"2026-09-18","cited_by_count":0,"area":null}],"next_cursor":null}