{"total":13,"rows":[{"id":"2511.04703","title":"Measuring what Matters: Construct Validity in Large Language Model Benchmarks","created":"2025-11-03","cited_by_count":119,"area":null},{"id":"2409.18433","title":"Easy2Hard-Bench: Standardized Difficulty Labels for Profiling LLM Performance and Generalization","created":"2024-09-27","cited_by_count":24,"area":null},{"id":"2505.21315","title":"Charting the Landscape of African NLP: Mapping Progress and Shaping the Road Ahead","created":"2025-05-27","cited_by_count":16,"area":null},{"id":"2505.16125","title":"KoBALT: Korean Benchmark For Advanced Linguistic Tasks","created":"2025-05-22","cited_by_count":13,"area":null},{"id":"2411.10163","title":"Compound-QA: A Benchmark for Evaluating LLMs on Compound Questions","created":"2024-11-15","cited_by_count":5,"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":"2509.21820","title":"Can LLMs Generate and Solve Linguistic Olympiad Puzzles?","created":"2025-09-26","cited_by_count":2,"area":null},{"id":"2604.02645","title":"Speaking of Language: Reflections on Metalanguage Research in NLP","created":"2026-04-03","cited_by_count":1,"area":null},{"id":"2509.05060","title":"Entropy2Vec: Crosslingual Language Modeling Entropy as End-to-End Learnable Language Representations","created":"2025-09-05","cited_by_count":0,"area":null},{"id":"2602.01132","title":"Don't Judge a Book by its Cover: Testing LLMs' Robustness Under Logical Obfuscation","created":"2026-02-01","cited_by_count":0,"area":null},{"id":"2602.12424","title":"RankLLM: Weighted Ranking of LLMs by Quantifying Question Difficulty","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2606.14257","title":"The Linguistics Olympiads: Towards a New Corpus for Linguistics Research?","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2609.06212","title":"SLATE: Are AI-Generated Slides Educationally Effective? A Benchmark for Language Teaching Quality and Learner Knowledge Acquisition","created":"2026-09-05","cited_by_count":0,"area":null}],"next_cursor":null}