{"total":25,"rows":[{"id":"2205.10964","title":"The Geometry of Multilingual Language Model Representations","created":"2022-05-22","cited_by_count":95,"area":null},{"id":"2401.12143","title":"Anisotropy Is Inherent to Self-Attention in Transformers","created":"2024-01-22","cited_by_count":63,"area":null},{"id":"2404.06228","title":"Understanding Cross-Lingual Alignment -- A Survey","created":"2024-04-09","cited_by_count":34,"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":"2402.14700","title":"Unveiling Linguistic Regions in Large Language Models","created":"2024-02-22","cited_by_count":22,"area":null},{"id":"2404.07647","title":"Why do small language models underperform? Studying Language Model Saturation via the Softmax Bottleneck","created":"2024-04-11","cited_by_count":21,"area":null},{"id":"2205.07208","title":"Fine-tuning Pre-trained Language Models for Few-shot Intent Detection: Supervised Pre-training and Isotropization","created":"2022-05-15","cited_by_count":19,"area":null},{"id":"2301.11975","title":"Byte Pair Encoding for Symbolic Music","created":"2023-01-27","cited_by_count":19,"area":null},{"id":"2306.00458","title":"Exploring Anisotropy and Outliers in Multilingual Language Models for Cross-Lingual Semantic Sentence Similarity","created":"2023-06-01","cited_by_count":17,"area":null},{"id":"2305.13286","title":"How do languages influence each other? Studying cross-lingual data sharing during LM fine-tuning","created":"2023-05-22","cited_by_count":14,"area":null},{"id":"2408.06273","title":"FuxiTranyu: A Multilingual Large Language Model Trained with Balanced Data","created":"2024-08-12","cited_by_count":10,"area":null},{"id":"2210.05098","title":"IsoVec: Controlling the Relative Isomorphism of Word Embedding Spaces","created":"2022-10-11","cited_by_count":7,"area":null},{"id":"2408.08073","title":"Extracting Sentence Embeddings from Pretrained Transformer Models","created":"2024-08-15","cited_by_count":7,"area":null},{"id":"2212.09686","title":"A Natural Bias for Language Generation Models","created":"2022-12-19","cited_by_count":6,"area":null},{"id":"2306.07656","title":"Is Anisotropy Inherent to Transformers?","created":"2023-06-13","cited_by_count":5,"area":null},{"id":"2603.26663","title":"Weight Tying Biases Token Embeddings Towards the Output Space","created":"2026-03-27","cited_by_count":3,"area":null},{"id":"2310.13228","title":"The Less the Merrier? Investigating Language Representation in Multilingual Models","created":"2023-10-20","cited_by_count":2,"area":null},{"id":"2502.05150","title":"CodeSCM: Causal Analysis for Multi-Modal Code Generation","created":"2025-02-07","cited_by_count":2,"area":null},{"id":"2505.10945","title":"Semantic Aware Linear Transfer by Recycling Pre-trained Language Models for Cross-lingual Transfer","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2503.17279","title":"CASE -- Condition-Aware Sentence Embeddings for Conditional Semantic Textual Similarity Measurement","created":"2025-03-21","cited_by_count":1,"area":null},{"id":"2603.24413","title":"Pingala: Prosody-Aware Decoding for Sanskrit Poetry Generation","created":"2026-03-25","cited_by_count":1,"area":null},{"id":"2602.05035","title":"Capacity Constraints and the Multilingual Penalty for Lexical Disambiguation","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2603.02258","title":"Universal Conceptual Structure in Neural Translation: Probing NLLB-200's Multilingual Geometry","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2608.06908","title":"Calibrating WEAT Against Anisotropy: ZCA Whitening as a Geometric Pre-Processing Step for Embedding Association Tests","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.23358","title":"The Geometry of Low-Resource Language Representations","created":"2026-08-24","cited_by_count":0,"area":null}],"next_cursor":null}