{"total":30,"rows":[{"id":"2303.11504","title":"Language Model Behavior: A Comprehensive Survey","created":"2023-03-20","cited_by_count":92,"area":null},{"id":"2401.06416","title":"Mission: Impossible Language Models","created":"2024-01-12","cited_by_count":32,"area":null},{"id":"2211.00974","title":"Processing Long Legal Documents with Pre-trained Transformers: Modding LegalBERT and Longformer","created":"2022-11-02","cited_by_count":20,"area":null},{"id":"2406.11687","title":"Tokenization Falling Short: On Subword Robustness in Large Language Models","created":"2024-06-17","cited_by_count":20,"area":null},{"id":"2311.18805","title":"Unnatural Error Correction: GPT-4 Can Almost Perfectly Handle Unnatural Scrambled Text","created":"2023-11-30","cited_by_count":19,"area":null},{"id":"2308.04813","title":"CLEVA: Chinese Language Models EVAluation Platform","created":"2023-08-09","cited_by_count":13,"area":null},{"id":"2403.00758","title":"Mitigating Reversal Curse in Large Language Models via Semantic-aware Permutation Training","created":"2024-03-01","cited_by_count":11,"area":null},{"id":"2305.14307","title":"Debiasing should be Good and Bad: Measuring the Consistency of Debiasing Techniques in Language Models","created":"2023-05-23","cited_by_count":7,"area":null},{"id":"2404.18570","title":"Analyzing Semantic Change through Lexical Replacements","created":"2024-04-29","cited_by_count":7,"area":null},{"id":"2407.09184","title":"Does Incomplete Syntax Influence Korean Language Model? Focusing on Word Order and Case Markers","created":"2024-07-12","cited_by_count":6,"area":null},{"id":"2211.04427","title":"Word Order Matters when you Increase Masking","created":"2022-11-08","cited_by_count":4,"area":null},{"id":"2309.11710","title":"ContextRef: Evaluating Referenceless Metrics For Image Description Generation","created":"2023-09-21","cited_by_count":3,"area":null},{"id":"2403.02009","title":"Topic Aware Probing: From Sentence Length Prediction to Idiom Identification how reliant are Neural Language Models on Topic?","created":"2024-03-04","cited_by_count":3,"area":null},{"id":"2506.01205","title":"Trick or Neat: Adversarial Ambiguity and Language Model Evaluation","created":"2025-06-01","cited_by_count":3,"area":null},{"id":"2510.07178","title":"Biasless Language Models Learn Unnaturally: How LLMs Fail to Distinguish the Possible from the Impossible","created":"2025-10-08","cited_by_count":3,"area":null},{"id":"2304.05221","title":"Towards preserving word order importance through Forced Invalidation","created":"2023-04-11","cited_by_count":2,"area":null},{"id":"2401.07923","title":"Word Boundary Information Isn't Useful for Encoder Language Models","created":"2024-01-15","cited_by_count":2,"area":null},{"id":"2211.05025","title":"Local Structure Matters Most in Most Languages","created":"2022-11-09","cited_by_count":1,"area":null},{"id":"2310.12864","title":"The Locality and Symmetry of Positional Encodings","created":"2023-10-19","cited_by_count":1,"area":null},{"id":"2402.02164","title":"Hierarchical Structure Enhances the Convergence and Generalizability of Linear Molecular Representation","created":"2024-02-03","cited_by_count":1,"area":null},{"id":"2403.00876","title":"Word Order and World Knowledge","created":"2024-03-01","cited_by_count":1,"area":null},{"id":"2511.08139","title":"On the Interplay between Positional Encodings, Morphological Complexity, and Word Order Flexibility","created":"2025-11-11","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":"2303.01191","title":"Denoising-based UNMT is more robust to word-order divergence than MASS-based UNMT","created":"2023-03-02","cited_by_count":0,"area":null},{"id":"2306.02302","title":"Does Character-level Information Always Improve DRS-based Semantic Parsing?","created":"2023-06-04","cited_by_count":0,"area":null},{"id":"2407.02136","title":"Black Big Boxes: Tracing Adjective Order Preferences in Large Language Models","created":"2024-07-02","cited_by_count":0,"area":null},{"id":"2408.09621","title":"Refining Packing and Shuffling Strategies for Enhanced Performance in Generative Language Models","created":"2024-08-19","cited_by_count":0,"area":null},{"id":"2411.05665","title":"Exploring the Limits of Large Language Models: A Systematic Evaluation of Masked Text Processing Ability through MskQA and MskCal","created":"2024-11-08","cited_by_count":0,"area":null},{"id":"2603.19427","title":"Vocabulary shapes cross-lingual variation of word-order learnability in language models","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2607.10268","title":"Language Re-generation: An investigation into information locality effects on reconstruction","created":"2026-07-11","cited_by_count":0,"area":null}],"next_cursor":null}