{"total":487,"rows":[{"id":"2311.03658","title":"The Linear Representation Hypothesis and the Geometry of Large Language Models","created":"2023-11-07","cited_by_count":716,"area":null},{"id":"2203.02053","title":"Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning","created":"2022-03-03","cited_by_count":561,"area":null},{"id":"2210.03057","title":"Language Models are Multilingual Chain-of-Thought Reasoners","created":"2022-10-06","cited_by_count":530,"area":"lr"},{"id":"2310.15213","title":"Function Vectors in Large Language Models","created":"2023-10-23","cited_by_count":308,"area":null},{"id":"2205.10643","title":"Self-Supervised Speech Representation Learning: A Review","created":"2022-05-21","cited_by_count":260,"area":null},{"id":"2304.05613","title":"ChatGPT Beyond English: Towards a Comprehensive Evaluation of Large Language Models in Multilingual Learning","created":"2023-04-12","cited_by_count":206,"area":null},{"id":"2209.15430","title":"Relative representations enable zero-shot latent space communication","created":"2022-09-30","cited_by_count":191,"area":null},{"id":"2202.10261","title":"A Self-Supervised Descriptor for Image Copy Detection","created":"2022-02-21","cited_by_count":176,"area":null},{"id":"2105.11084","title":"Unsupervised Speech Recognition","created":"2021-05-24","cited_by_count":148,"area":null},{"id":"2304.03738","title":"Should ChatGPT be Biased? Challenges and Risks of Bias in Large Language Models","created":"2023-04-07","cited_by_count":148,"area":null},{"id":"2103.11943","title":"BERT: A Review of Applications in Natural Language Processing and Understanding","created":"2021-03-22","cited_by_count":109,"area":null},{"id":"2106.15115","title":"Neural Machine Translation for Low-Resource Languages: A Survey","created":"2021-06-29","cited_by_count":109,"area":null},{"id":"2109.00486","title":"Survey of Low-Resource Machine Translation","created":"2021-09-01","cited_by_count":92,"area":null},{"id":"2112.06598","title":"WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models","created":"2021-12-13","cited_by_count":89,"area":null},{"id":"2104.08027","title":"Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders","created":"2021-04-16","cited_by_count":88,"area":null},{"id":"2404.00929","title":"A Survey on Multilingual Large Language Models: Corpora, Alignment, and Bias","created":"2024-04-01","cited_by_count":84,"area":null},{"id":"2104.08771","title":"Cross-Attention is All You Need: Adapting Pretrained Transformers for Machine Translation","created":"2021-04-18","cited_by_count":74,"area":null},{"id":"2302.07856","title":"Dictionary-based Phrase-level Prompting of Large Language Models for Machine Translation","created":"2023-02-15","cited_by_count":74,"area":null},{"id":"2112.02721","title":"NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation","created":"2021-12-06","cited_by_count":73,"area":null},{"id":"2112.12777","title":"Cross Modal Retrieval with Querybank Normalisation","created":"2021-12-23","cited_by_count":72,"area":null},{"id":"2411.04986","title":"The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and Modalities","created":"2024-11-07","cited_by_count":69,"area":null},{"id":"2102.08886","title":"Towards generalisable hate speech detection: a review on obstacles and solutions","created":"2021-02-17","cited_by_count":66,"area":null},{"id":"2106.01128","title":"Linear-Time Gromov Wasserstein Distances using Low Rank Couplings and Costs","created":"2021-06-02","cited_by_count":61,"area":null},{"id":"2202.02312","title":"A Dataset for Interactive Vision-Language Navigation with Unknown Command Feasibility","created":"2022-02-04","cited_by_count":61,"area":null},{"id":"2103.13309","title":"Are Multilingual Models Effective in Code-Switching?","created":"2021-03-24","cited_by_count":56,"area":null},{"id":"2407.15390","title":"ALLaM: Large Language Models for Arabic and English","created":"2024-07-22","cited_by_count":55,"area":null},{"id":"2505.12540","title":"Harnessing the Universal Geometry of Embeddings","created":"2025-05-18","cited_by_count":55,"area":null},{"id":"2106.02124","title":"How to Adapt Your Pretrained Multilingual Model to 1600 Languages","created":"2021-06-03","cited_by_count":54,"area":null},{"id":"2311.00664","title":"Latent Space Translation via Semantic Alignment","created":"2023-11-01","cited_by_count":52,"area":null},{"id":"2104.08726","title":"AmericasNLI: Evaluating Zero-shot Natural Language Understanding of Pretrained Multilingual Models in Truly Low-resource Languages","created":"2021-04-18","cited_by_count":50,"area":null},{"id":"2105.07615","title":"Differentially Private Federated Knowledge Graphs Embedding","created":"2021-05-17","cited_by_count":45,"area":null},{"id":"2106.09672","title":"The 2021 Image Similarity Dataset and Challenge","created":"2021-06-17","cited_by_count":44,"area":null},{"id":"2401.05224","title":"Do Vision and Language Encoders Represent the World Similarly?","created":"2024-01-10","cited_by_count":44,"area":null},{"id":"2108.13655","title":"MELM: Data Augmentation with Masked Entity Language Modeling for Low-Resource NER","created":"2021-08-31","cited_by_count":42,"area":null},{"id":"2302.02069","title":"Heterogeneous Federated Knowledge Graph Embedding Learning and Unlearning","created":"2023-02-04","cited_by_count":40,"area":"safety"},{"id":"2403.10691","title":"MYTE: Morphology-Driven Byte Encoding for Better and Fairer Multilingual Language Modeling","created":"2024-03-15","cited_by_count":40,"area":null},{"id":"2304.01752","title":"Black Box Few-Shot Adaptation for Vision-Language models","created":"2023-04-04","cited_by_count":39,"area":"mllm"},{"id":"2505.17306","title":"Refusal Direction is Universal Across Safety-Aligned Languages","created":"2025-05-22","cited_by_count":38,"area":null},{"id":"2103.15452","title":"Boosting the Speed of Entity Alignment 10*: Dual Attention Matching Network with Normalized Hard Sample Mining","created":"2021-03-29","cited_by_count":37,"area":null},{"id":"2207.09858","title":"GenHPF: General Healthcare Predictive Framework with Multi-task Multi-source Learning","created":"2022-07-20","cited_by_count":36,"area":null},{"id":"2212.09660","title":"The Decades Progress on Code-Switching Research in NLP: A Systematic Survey on Trends and Challenges","created":"2022-12-19","cited_by_count":35,"area":null},{"id":"2404.06228","title":"Understanding Cross-Lingual Alignment -- A Survey","created":"2024-04-09","cited_by_count":34,"area":null},{"id":"2105.09984","title":"Multi-modal Sarcasm Detection and Humor Classification in Code-mixed Conversations","created":"2021-05-20","cited_by_count":33,"area":null},{"id":"2102.05456","title":"Civil Rephrases Of Toxic Texts With Self-Supervised Transformers","created":"2021-02-01","cited_by_count":32,"area":null},{"id":"2402.19167","title":"Teaching Large Language Models an Unseen Language on the Fly","created":"2024-02-29","cited_by_count":30,"area":null},{"id":"2105.03953","title":"Continual Mixed-Language Pre-Training for Extremely Low-Resource Neural Machine Translation","created":"2021-05-09","cited_by_count":29,"area":null},{"id":"2107.06483","title":"From Machine Translation to Code-Switching: Generating High-Quality Code-Switched Text","created":"2021-07-14","cited_by_count":29,"area":null},{"id":"2108.01661","title":"Grounding Representation Similarity with Statistical Testing","created":"2021-08-03","cited_by_count":29,"area":null},{"id":"2502.14830","title":"Middle-Layer Representation Alignment for Cross-Lingual Transfer in Fine-Tuned LLMs","created":"2025-02-20","cited_by_count":29,"area":null},{"id":"2105.14398","title":"Learning Domain-Specialised Representations for Cross-Lingual Biomedical Entity Linking","created":"2021-05-30","cited_by_count":28,"area":null},{"id":"2302.06555","title":"Do Vision and Language Models Share Concepts? A Vector Space Alignment Study","created":"2023-02-13","cited_by_count":27,"area":null},{"id":"2411.02460","title":"Code-Switching Curriculum Learning for Multilingual Transfer in LLMs","created":"2024-11-04","cited_by_count":27,"area":null},{"id":"2203.10753","title":"Match the Script, Adapt if Multilingual: Analyzing the Effect of Multilingual Pretraining on Cross-lingual Transferability","created":"2022-03-21","cited_by_count":26,"area":null},{"id":"2209.02842","title":"ASR2K: Speech Recognition for Around 2000 Languages without Audio","created":"2022-09-06","cited_by_count":26,"area":null},{"id":"2103.07792","title":"Multilingual Code-Switching for Zero-Shot Cross-Lingual Intent Prediction and Slot Filling","created":"2021-03-13","cited_by_count":25,"area":null},{"id":"2203.14987","title":"Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment","created":"2022-03-28","cited_by_count":24,"area":null},{"id":"2211.06993","title":"GreenPLM: Cross-Lingual Transfer of Monolingual Pre-Trained Language Models at Almost No Cost","created":"2022-11-13","cited_by_count":24,"area":null},{"id":"2304.03544","title":"InfoCTM: A Mutual Information Maximization Perspective of Cross-Lingual Topic Modeling","created":"2023-04-07","cited_by_count":24,"area":null},{"id":"2410.12462","title":"Bridging the Language Gaps in Large Language Models with Inference-Time Cross-Lingual Intervention","created":"2024-10-16","cited_by_count":24,"area":null},{"id":"2504.03022","title":"The Dual-Route Model of Induction","created":"2025-04-03","cited_by_count":24,"area":null},{"id":"2103.09593","title":"Code-Mixing on Sesame Street: Dawn of the Adversarial Polyglots","created":"2021-03-17","cited_by_count":23,"area":null},{"id":"2203.00242","title":"Unsupervised Vision-and-Language Pre-training via Retrieval-based Multi-Granular Alignment","created":"2022-03-01","cited_by_count":23,"area":null},{"id":"2208.12526","title":"Cross-Lingual Cross-Modal Retrieval with Noise-Robust Learning","created":"2022-08-26","cited_by_count":22,"area":null},{"id":"2108.01887","title":"PARADISE: Exploiting Parallel Data for Multilingual Sequence-to-Sequence Pretraining","created":"2021-08-04","cited_by_count":21,"area":null},{"id":"2112.14330","title":"Simple, Interpretable and Stable Method for Detecting Words with Usage Change across Corpora","created":"2021-12-28","cited_by_count":21,"area":null},{"id":"2305.13627","title":"InstructAlign: High-and-Low Resource Language Alignment via Continual Crosslingual Instruction Tuning","created":"2023-05-23","cited_by_count":21,"area":null},{"id":"2106.02248","title":"Knowing the No-match: Entity Alignment with Dangling Cases","created":"2021-06-04","cited_by_count":20,"area":null},{"id":"2205.10312","title":"ClusterEA: Scalable Entity Alignment with Stochastic Training and Normalized Mini-batch Similarities","created":"2022-05-20","cited_by_count":20,"area":null},{"id":"2305.15020","title":"An Efficient Multilingual Language Model Compression through Vocabulary Trimming","created":"2023-05-24","cited_by_count":20,"area":null},{"id":"2310.11612","title":"Balance Act: Mitigating Hubness in Cross-Modal Retrieval with Query and Gallery Banks","created":"2023-10-17","cited_by_count":20,"area":null},{"id":"2101.00148","title":"Bilingual Lexicon Induction via Unsupervised Bitext Construction and Word Alignment","created":"2021-01-01","cited_by_count":19,"area":null},{"id":"2104.07554","title":"Zero-Shot Cross-lingual Semantic Parsing","created":"2021-04-15","cited_by_count":19,"area":null},{"id":"2105.07688","title":"OntoEA: Ontology-guided Entity Alignment via Joint Knowledge Graph Embedding","created":"2021-05-17","cited_by_count":19,"area":null},{"id":"2105.11301","title":"DaN+: Danish Nested Named Entities and Lexical Normalization","created":"2021-05-24","cited_by_count":19,"area":null},{"id":"2106.06797","title":"Machine Translation into Low-resource Language Varieties","created":"2021-06-12","cited_by_count":19,"area":null},{"id":"2302.00796","title":"Unsupervised Entity Alignment for Temporal Knowledge Graphs","created":"2023-02-01","cited_by_count":19,"area":null},{"id":"2302.08774","title":"Vision, Deduction and Alignment: An Empirical Study on Multi-modal Knowledge Graph Alignment","created":"2023-02-17","cited_by_count":19,"area":null},{"id":"2305.13175","title":"Discovering Universal Geometry in Embeddings with ICA","created":"2023-05-22","cited_by_count":19,"area":null},{"id":"2311.18034","title":"Hyperpolyglot LLMs: Cross-Lingual Interpretability in Token Embeddings","created":"2023-11-29","cited_by_count":19,"area":null},{"id":"2505.11454","title":"HumaniBench: A Human-Centric Framework for Large Multimodal Models Evaluation","created":"2025-05-16","cited_by_count":19,"area":"mllm"},{"id":"2106.04302","title":"Obtaining Better Static Word Embeddings Using Contextual Embedding Models","created":"2021-06-08","cited_by_count":18,"area":null},{"id":"2203.08307","title":"Improving Word Translation via Two-Stage Contrastive Learning","created":"2022-03-15","cited_by_count":18,"area":null},{"id":"2306.02790","title":"Exploring the Relationship between Alignment and Cross-lingual Transfer in Multilingual Transformers","created":"2023-06-05","cited_by_count":18,"area":null},{"id":"2206.02355","title":"Relation Matters: Foreground-aware Graph-based Relational Reasoning for Domain Adaptive Object Detection","created":"2022-06-06","cited_by_count":17,"area":null},{"id":"2210.06545","title":"GULP: a prediction-based metric between representations","created":"2022-10-12","cited_by_count":17,"area":null},{"id":"2107.04239","title":"A Survey on Low-Resource Neural Machine Translation","created":"2021-07-09","cited_by_count":16,"area":null},{"id":"2203.02150","title":"Time-aware Graph Neural Networks for Entity Alignment between Temporal Knowledge Graphs","created":"2022-03-04","cited_by_count":16,"area":null},{"id":"2304.08823","title":"Transfer to a Low-Resource Language via Close Relatives: The Case Study on Faroese","created":"2023-04-18","cited_by_count":15,"area":null},{"id":"2305.16651","title":"TADA: Task-Agnostic Dialect Adapters for English","created":"2023-05-26","cited_by_count":15,"area":null},{"id":"2305.19589","title":"SLABERT Talk Pretty One Day: Modeling Second Language Acquisition with BERT","created":"2023-05-31","cited_by_count":15,"area":null},{"id":"2402.15048","title":"Unlocking the Power of Large Language Models for Entity Alignment","created":"2024-02-23","cited_by_count":15,"area":null},{"id":"2404.11225","title":"In-Context Learning State Vector with Inner and Momentum Optimization","created":"2024-04-17","cited_by_count":15,"area":null},{"id":"2103.10531","title":"Improving the Lexical Ability of Pretrained Language Models for Unsupervised Neural Machine Translation","created":"2021-03-18","cited_by_count":14,"area":null},{"id":"2110.07804","title":"Alternative Input Signals Ease Transfer in Multilingual Machine Translation","created":"2021-10-15","cited_by_count":14,"area":null},{"id":"2204.08325","title":"GL-CLeF: A Global-Local Contrastive Learning Framework for Cross-lingual Spoken Language Understanding","created":"2022-04-18","cited_by_count":14,"area":null},{"id":"2108.08468","title":"QUEACO: Borrowing Treasures from Weakly-labeled Behavior Data for Query Attribute Value Extraction","created":"2021-08-19","cited_by_count":13,"area":null},{"id":"2109.04653","title":"Towards Developing a Multilingual and Code-Mixed Visual Question Answering System by Knowledge Distillation","created":"2021-09-10","cited_by_count":13,"area":"distill"},{"id":"2410.01079","title":"Concept Space Alignment in Multilingual LLMs","created":"2024-10-01","cited_by_count":13,"area":null},{"id":"2504.16318","title":"Semantics at an Angle: When Cosine Similarity Works Until It Doesn't","created":"2025-04-22","cited_by_count":13,"area":null},{"id":"2106.03084","title":"Combining Static Word Embeddings and Contextual Representations for Bilingual Lexicon Induction","created":"2021-06-06","cited_by_count":12,"area":null}],"next_cursor":"100"}