{"list":"other","total":55,"rows":[{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"1911.11641","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","created":"2019-11-26","cited_by_count":2883},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"2406.17557","title":"The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale","created":"2024-06-25","cited_by_count":1160},{"id":"1809.05053","title":"XNLI: Evaluating Cross-lingual Sentence Representations","created":"2018-09-13","cited_by_count":915},{"id":"2310.06824","title":"The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets","created":"2023-10-10","cited_by_count":712},{"id":"1910.11856","title":"On the Cross-lingual Transferability of Monolingual Representations","created":"2019-10-25","cited_by_count":578},{"id":"2305.01610","title":"Finding Neurons in a Haystack: Case Studies with Sparse Probing","created":"2023-05-02","cited_by_count":334},{"id":"2310.15916","title":"In-Context Learning Creates Task Vectors","created":"2023-10-24","cited_by_count":312},{"id":"2401.06102","title":"Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models","created":"2024-01-11","cited_by_count":235},{"id":"2305.15425","title":"Language Model Tokenizers Introduce Unfairness Between Languages","created":"2023-05-17","cited_by_count":214},{"id":"2305.13707","title":"Do All Languages Cost the Same? Tokenization in the Era of Commercial Language Models","created":"2023-05-23","cited_by_count":192},{"id":"2412.03304","title":"Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluation","created":"2024-12-04","cited_by_count":191},{"id":"2506.20920","title":"FineWeb2: One Pipeline to Scale Them All -- Adapting Pre-Training Data Processing to Every Language","created":"2025-06-26","cited_by_count":143},{"id":"2304.00740","title":"Inspecting and Editing Knowledge Representations in Language Models","created":"2023-04-03","cited_by_count":141},{"id":"2405.15032","title":"Aya 23: Open Weight Releases to Further Multilingual Progress","created":"2024-05-23","cited_by_count":123},{"id":"2407.13623","title":"Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies","created":"2024-07-18","cited_by_count":118},{"id":"2409.16235","title":"EuroLLM: Multilingual Language Models for Europe","created":"2024-09-24","cited_by_count":106},{"id":"2305.16130","title":"Language Models Implement Simple Word2Vec-style Vector Arithmetic","created":"2023-05-25","cited_by_count":98},{"id":"2502.15603","title":"Do Multilingual LLMs Think In English?","created":"2025-02-21","cited_by_count":78},{"id":"1606.02858","title":"A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task","created":"2016-06-09","cited_by_count":72},{"id":"2101.00403","title":"Superbizarre Is Not Superb: Derivational Morphology Improves BERT's Interpretation of Complex Words","created":"2021-01-02","cited_by_count":63},{"id":"2503.13423","title":"SuperBPE: Space Travel for Language Models","created":"2025-03-17","cited_by_count":63},{"id":"2204.08832","title":"Impact of Tokenization on Language Models: An Analysis for Turkish","created":"2022-04-19","cited_by_count":62},{"id":"2305.17179","title":"Tokenization Impacts Multilingual Language Modeling: Assessing Vocabulary Allocation and Overlap Across Languages","created":"2023-05-26","cited_by_count":62},{"id":"2410.05864","title":"From Tokens to Words: On the Inner Lexicon of LLMs","created":"2024-10-08","cited_by_count":48},{"id":"2501.16975","title":"Over-Tokenized Transformer: Vocabulary is Generally Worth Scaling","created":"2025-01-28","cited_by_count":44},{"id":"1911.00225","title":"When Choosing Plausible Alternatives, Clever Hans can be Clever","created":"2019-11-01","cited_by_count":40},{"id":"2411.09009","title":"Cut Your Losses in Large-Vocabulary Language Models","created":"2024-11-13","cited_by_count":40},{"id":"2012.06262","title":"Morphology Matters: A Multilingual Language Modeling Analysis","created":"2020-12-11","cited_by_count":37},{"id":"2311.08849","title":"OFA: A Framework of Initializing Unseen Subword Embeddings for Efficient Large-scale Multilingual Continued Pretraining","created":"2023-11-15","cited_by_count":37},{"id":"1509.01692","title":"Take and Took, Gaggle and Goose, Book and Read: Evaluating the Utility of Vector Differences for Lexical Relation Learning","created":"2015-09-05","cited_by_count":29},{"id":"2502.00894","title":"MorphBPE: A Morpho-Aware Tokenizer Bridging Linguistic Complexity for Efficient LLM Training Across Morphologies","created":"2025-02-02","cited_by_count":25},{"id":"2508.04796","title":"Parity-Aware Byte-Pair Encoding: Improving Cross-lingual Fairness in Tokenization","created":"2025-08-06","cited_by_count":20},{"id":"2406.20086","title":"Token Erasure as a Footprint of Implicit Vocabulary Items in LLMs","created":"2024-06-28","cited_by_count":18},{"id":"1908.05453","title":"What's Wrong with Hebrew NLP? And How to Make it Right","created":"2019-08-15","cited_by_count":16},{"id":"2503.19693","title":"AdaptiVocab: Enhancing LLM Efficiency in Focused Domains through Lightweight Vocabulary Adaptation","created":"2025-03-25","cited_by_count":15},{"id":"2106.07540","title":"Evaluating Various Tokenizers for Arabic Text Classification","created":"2021-06-14","cited_by_count":14},{"id":"2203.08954","title":"BPE vs. Morphological Segmentation: A Case Study on Machine Translation of Four Polysynthetic Languages","created":"2022-03-16","cited_by_count":14},{"id":"1909.02134","title":"PaLM: A Hybrid Parser and Language Model","created":"2019-09-04","cited_by_count":13},{"id":"2410.01188","title":"Gold Panning in Vocabulary: An Adaptive Method for Vocabulary Expansion of Domain-Specific LLMs","created":"2024-10-02","cited_by_count":12},{"id":"1906.01037","title":"Better Character Language Modeling Through Morphology","created":"2019-06-03","cited_by_count":9},{"id":"2410.09644","title":"Adapters for Altering LLM Vocabularies: What Languages Benefit the Most?","created":"2024-10-12","cited_by_count":9},{"id":"2503.14433","title":"Splintering Nonconcatenative Languages for Better Tokenization","created":"2025-03-18","cited_by_count":6},{"id":"2210.15379","title":"MorphTE: Injecting Morphology in Tensorized Embeddings","created":"2022-10-27","cited_by_count":5},{"id":"2403.11130","title":"Exploring Tokenization Strategies and Vocabulary Sizes for Enhanced Arabic Language Models","created":"2024-03-17","cited_by_count":5},{"id":"2507.16323","title":"SpeLLM: Character-Level Multi-Head Decoding","created":"2025-07-22","cited_by_count":2}],"next_cursor":null}