{"total":17,"rows":[{"id":"2406.04244","title":"Benchmark Data Contamination of Large Language Models: A Survey","created":"2024-06-06","cited_by_count":147,"area":null},{"id":"2411.00860","title":"Survey of Cultural Awareness in Language Models: Text and Beyond","created":"2024-10-30","cited_by_count":103,"area":null},{"id":"2411.19799","title":"INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge","created":"2024-11-29","cited_by_count":86,"area":null},{"id":"2410.05873","title":"MEXA: Multilingual Evaluation of English-Centric LLMs via Cross-Lingual Alignment","created":"2024-10-08","cited_by_count":25,"area":null},{"id":"2507.23248","title":"Script Fragmentation and Format: What Drives the English-Bengali Performance Gap in Open LLMs?","created":"2025-07-31","cited_by_count":9,"area":null},{"id":"2502.07459","title":"PerCul: A Story-Driven Cultural Evaluation of LLMs in Persian","created":"2025-02-11","cited_by_count":8,"area":null},{"id":"2506.20274","title":"Enterprise Large Language Model Evaluation Benchmark","created":"2025-06-25","cited_by_count":5,"area":null},{"id":"2508.00673","title":"MELAC: Massive Evaluation of Large Language Models with Alignment of Culture in Persian Language","created":"2025-08-01","cited_by_count":3,"area":null},{"id":"2408.08848","title":"PsychoLex: Unveiling the Psychological Mind of Large Language Models","created":"2024-08-16","cited_by_count":2,"area":null},{"id":"2503.11911","title":"LAG-MMLU: Benchmarking Frontier LLM Understanding in Latvian and Giriama","created":"2025-03-14","cited_by_count":2,"area":null},{"id":"2502.12895","title":"Multilingual European Language Models: Benchmarking Approaches and Challenges","created":"2025-02-18","cited_by_count":1,"area":null},{"id":"2510.19616","title":"PBBQ: A Persian Bias Benchmark Dataset Curated with Human-AI Collaboration for Large Language Models","created":"2025-10-22","cited_by_count":1,"area":null},{"id":"2602.17623","title":"Unmasking the Factual-Conceptual Gap in Persian Language Models","created":"2026-02-19","cited_by_count":1,"area":null},{"id":"2603.09979","title":"GhazalBench: Canonical Verse Access in LLMs across Persian Ghazals and Shakespearean Sonnets","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2509.21104","title":"PerHalluEval: Persian Hallucination Evaluation Benchmark for Large Language Models","created":"2025-09-25","cited_by_count":0,"area":null},{"id":"2510.15134","title":"FarsiMCQGen: a Persian Multiple-choice Question Generation Framework","created":"2025-10-16","cited_by_count":0,"area":null},{"id":"2608.24698","title":"The Annotation Bottleneck in Persian Text NLP: Persian as an Annotation-Scarce Language","created":"2026-08-25","cited_by_count":0,"area":null}],"next_cursor":null}