{"total":46,"rows":[{"id":"2504.02768","title":"MultiBLiMP 1.0: A Massively Multilingual Benchmark of Linguistic Minimal Pairs","created":"2025-04-03","cited_by_count":71,"area":null},{"id":"2210.12814","title":"RuCoLA: Russian Corpus of Linguistic Acceptability","created":"2022-10-23","cited_by_count":26,"area":null},{"id":"2406.19232","title":"RuBLiMP: Russian Benchmark of Linguistic Minimal Pairs","created":"2024-06-27","cited_by_count":24,"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":"2309.06085","title":"BHASA: A Holistic Southeast Asian Linguistic and Cultural Evaluation Suite for Large Language Models","created":"2023-09-12","cited_by_count":18,"area":null},{"id":"2304.00906","title":"ScandEval: A Benchmark for Scandinavian Natural Language Processing","created":"2023-04-03","cited_by_count":16,"area":null},{"id":"2109.07465","title":"On the Limits of Minimal Pairs in Contrastive Evaluation","created":"2021-09-15","cited_by_count":15,"area":null},{"id":"2210.11689","title":"SLING: Sino Linguistic Evaluation of Large Language Models","created":"2022-10-21","cited_by_count":15,"area":null},{"id":"2311.09033","title":"MELA: Multilingual Evaluation of Linguistic Acceptability","created":"2023-11-15","cited_by_count":14,"area":null},{"id":"2408.09639","title":"How to Make the Most of LLMs' Grammatical Knowledge for Acceptability Judgments","created":"2024-08-19","cited_by_count":14,"area":null},{"id":"2502.20344","title":"LinguaLens: Towards Interpreting Linguistic Mechanisms of Large Language Models via Sparse Auto-Encoder","created":"2025-02-27","cited_by_count":14,"area":null},{"id":"2411.06096","title":"A Systematic Assessment of Language Models with Linguistic Minimal Pairs in Chinese","created":"2024-11-09","cited_by_count":13,"area":null},{"id":"2305.14150","title":"WYWEB: A NLP Evaluation Benchmark For Classical Chinese","created":"2023-05-23","cited_by_count":12,"area":null},{"id":"2502.19737","title":"XCOMPS: A Multilingual Benchmark of Conceptual Minimal Pairs","created":"2025-02-27","cited_by_count":12,"area":null},{"id":"2309.12676","title":"JCoLA: Japanese Corpus of Linguistic Acceptability","created":"2023-09-22","cited_by_count":11,"area":null},{"id":"2109.14017","title":"Shaking Syntactic Trees on the Sesame Street: Multilingual Probing with Controllable Perturbations","created":"2021-09-28","cited_by_count":10,"area":null},{"id":"2411.07474","title":"Controlled Evaluation of Syntactic Knowledge in Multilingual Language Models","created":"2024-11-12","cited_by_count":10,"area":null},{"id":"2502.04795","title":"Developmentally-plausible Working Memory Shapes a Critical Period for Language Acquisition","created":"2025-02-07","cited_by_count":10,"area":null},{"id":"2506.13487","title":"TurBLiMP: A Turkish Benchmark of Linguistic Minimal Pairs","created":"2025-06-16","cited_by_count":9,"area":null},{"id":"2405.05572","title":"From Human Judgements to Predictive Models: Unravelling Acceptability in Code-Mixed Sentences","created":"2024-05-09","cited_by_count":8,"area":null},{"id":"2506.01840","title":"Minimal Pair-Based Evaluation of Code-Switching","created":"2025-06-02","cited_by_count":8,"area":null},{"id":"2506.18105","title":"Chengyu-Bench: Benchmarking Large Language Models for Chinese Idiom Understanding and Use","created":"2025-06-22","cited_by_count":8,"area":null},{"id":"2307.05454","title":"Empowering Cross-lingual Behavioral Testing of NLP Models with Typological Features","created":"2023-07-11","cited_by_count":6,"area":null},{"id":"2109.11058","title":"Controlled Evaluation of Grammatical Knowledge in Mandarin Chinese Language Models","created":"2021-09-22","cited_by_count":5,"area":null},{"id":"2509.15655","title":"Layer-wise Minimal Pair Probing Reveals Contextual Grammatical-Conceptual Hierarchy in Speech Representations","created":"2025-09-19","cited_by_count":5,"area":null},{"id":"2411.07533","title":"Large Language Models as Neurolinguistic Subjects: Discrepancy between Performance and Competence","created":"2024-11-12","cited_by_count":4,"area":null},{"id":"2503.10838","title":"Who Relies More on World Knowledge and Bias for Syntactic Ambiguity Resolution: Humans or LLMs?","created":"2025-03-13","cited_by_count":3,"area":null},{"id":"2201.01845","title":"Data-driven Model Generalizability in Crosslinguistic Low-resource Morphological Segmentation","created":"2022-01-05","cited_by_count":2,"area":null},{"id":"2401.07777","title":"Quantum Transfer Learning for Acceptability Judgements","created":"2024-01-15","cited_by_count":2,"area":null},{"id":"2504.02116","title":"Language Models at the Syntax-Semantics Interface: A Case Study of the Long-Distance Binding of Chinese Reflexive ziji","created":"2025-04-02","cited_by_count":2,"area":null},{"id":"2508.01006","title":"UrBLiMP: A Benchmark for Evaluating the Linguistic Competence of Large Language Models in Urdu","created":"2025-08-01","cited_by_count":2,"area":null},{"id":"2508.16867","title":"QFrCoLA: a Quebec-French Corpus of Linguistic Acceptability Judgments","created":"2025-08-23","cited_by_count":2,"area":null},{"id":"2509.25664","title":"QFrBLiMP: a Quebec-French Benchmark of Linguistic Minimal Pairs","created":"2025-09-30","cited_by_count":2,"area":null},{"id":"2510.20957","title":"Irish-BLiMP: A Linguistic Benchmark for Evaluating Human and Language Model Performance in a Low-Resource Setting","created":"2025-10-23","cited_by_count":2,"area":null},{"id":"2409.12435","title":"Linguistic Minimal Pairs Elicit Linguistic Similarity in Large Language Models","created":"2024-09-19","cited_by_count":1,"area":null},{"id":"2601.19926","title":"The Grammar of Transformers: A Systematic Review of Interpretability Research on Syntactic Knowledge in Language Models","created":"2026-01-09","cited_by_count":1,"area":null},{"id":"2606.05087","title":"Light or Full Verb? A Minimal-Pair Dataset for Probing Phraseological Competence in Language Models","created":"2026-06-03","cited_by_count":1,"area":null},{"id":"2608.03803","title":"M-GATE: Multilingual Grammar, Accuracy in Translation, and Efficiency Benchmark for Large Language Models","created":"2026-08-04","cited_by_count":1,"area":null},{"id":"2305.14091","title":"Revisiting Acceptability Judgements","created":"2023-05-23","cited_by_count":0,"area":null},{"id":"2505.16277","title":"Spontaneous Speech Variables for Evaluating LLMs Cognitive Plausibility","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2507.11867","title":"COLA-GEC: A Bidirectional Framework for Enhancing Grammatical Acceptability and Error Correction","created":"2025-07-16","cited_by_count":0,"area":null},{"id":"2510.20670","title":"\\textsc{CantoNLU}: A benchmark for Cantonese natural language understanding","created":"2025-10-23","cited_by_count":0,"area":null},{"id":"2510.24856","title":"Do Large Language Models Grasp The Grammar? Evidence from Grammar-Book-Guided Probing in Luxembourgish","created":"2025-10-28","cited_by_count":0,"area":null},{"id":"2603.25227","title":"Comparing Natural and Synthetic Structured Data: A Study of the Passive Verb Alternation in French and Italian","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2604.27232","title":"Targeted Linguistic Analysis of Sign Language Models with Minimal Translation Pairs","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2610.13607","title":"BLiMPPI: Benchmark of Linguistic Minimal Pairs for Polarity Items","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}