{"total":143,"rows":[{"id":"2210.02410","title":"The Vendi Score: A Diversity Evaluation Metric for Machine Learning","created":"2022-10-05","cited_by_count":311,"area":null},{"id":"2603.28052","title":"Meta-Harness: End-to-End Optimization of Model Harnesses","created":"2026-03-30","cited_by_count":309,"area":null},{"id":"2305.15005","title":"Sentiment Analysis in the Era of Large Language Models: A Reality Check","created":"2023-05-24","cited_by_count":268,"area":null},{"id":"2402.09906","title":"Generative Representational Instruction Tuning","created":"2024-02-15","cited_by_count":233,"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":"2209.11055","title":"Efficient Few-Shot Learning Without Prompts","created":"2022-09-22","cited_by_count":137,"area":null},{"id":"2212.05409","title":"Towards Leaving No Indic Language Behind: Building Monolingual Corpora, Benchmark and Models for Indic Languages","created":"2022-12-11","cited_by_count":102,"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":"2310.14542","title":"Evaluating Large Language Models on Controlled Generation Tasks","created":"2023-10-23","cited_by_count":73,"area":null},{"id":"2305.05940","title":"Multilingual LLMs are Better Cross-lingual In-context Learners with Alignment","created":"2023-05-10","cited_by_count":71,"area":null},{"id":"2102.02514","title":"FedAUX: Leveraging Unlabeled Auxiliary Data in Federated Learning","created":"2021-02-04","cited_by_count":69,"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":"2305.14857","title":"BUFFET: Benchmarking Large Language Models for Few-shot Cross-lingual Transfer","created":"2023-05-24","cited_by_count":68,"area":null},{"id":"2403.16512","title":"LLMs Are Few-Shot In-Context Low-Resource Language Learners","created":"2024-03-25","cited_by_count":68,"area":null},{"id":"2404.04925","title":"Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontiers","created":"2024-04-07","cited_by_count":51,"area":"lr"},{"id":"2305.14240","title":"Revisiting Machine Translation for Cross-lingual Classification","created":"2023-05-23","cited_by_count":41,"area":null},{"id":"2305.11242","title":"Comparing Biases and the Impact of Multilingual Training across Multiple Languages","created":"2023-05-18","cited_by_count":36,"area":null},{"id":"2403.09162","title":"Unveiling the Generalization Power of Fine-Tuned Large Language Models","created":"2024-03-14","cited_by_count":36,"area":null},{"id":"2402.14873","title":"Technical Report on the Pangram AI-Generated Text Classifier","created":"2024-02-21","cited_by_count":34,"area":null},{"id":"2503.05500","title":"EuroBERT: Scaling Multilingual Encoders for European Languages","created":"2025-03-07","cited_by_count":31,"area":null},{"id":"2301.13720","title":"Zero-shot cross-lingual transfer language selection using linguistic similarity","created":"2023-01-31","cited_by_count":28,"area":null},{"id":"2202.11451","title":"Zero-shot Cross-lingual Transfer of Prompt-based Tuning with a Unified Multilingual Prompt","created":"2022-02-23","cited_by_count":25,"area":null},{"id":"2211.15649","title":"Beyond Counting Datasets: A Survey of Multilingual Dataset Construction and Necessary Resources","created":"2022-11-28","cited_by_count":25,"area":null},{"id":"2407.06488","title":"Towards Understanding Multi-Task Learning (Generalization) of LLMs via Detecting and Exploring Task-Specific Neurons","created":"2024-07-09","cited_by_count":25,"area":null},{"id":"2109.05929","title":"Cross-Market Product Recommendation","created":"2021-09-13","cited_by_count":22,"area":null},{"id":"2104.07908","title":"MetaXL: Meta Representation Transformation for Low-resource Cross-lingual Learning","created":"2021-04-16","cited_by_count":21,"area":null},{"id":"2306.09572","title":"How do different tokenizers perform on downstream tasks in scriptio continua languages?: A case study in Japanese","created":"2023-06-16","cited_by_count":20,"area":null},{"id":"2310.01208","title":"Label Supervised LLaMA Finetuning","created":"2023-10-02","cited_by_count":20,"area":null},{"id":"2407.21530","title":"Data Contamination Report from the 2024 CONDA Shared Task","created":"2024-07-31","cited_by_count":20,"area":null},{"id":"2210.12265","title":"On the Calibration of Massively Multilingual Language Models","created":"2022-10-21","cited_by_count":19,"area":null},{"id":"2305.14463","title":"ReadMe++: Benchmarking Multilingual Language Models for Multi-Domain Readability Assessment","created":"2023-05-23","cited_by_count":19,"area":null},{"id":"2212.09651","title":"Cross-Lingual Retrieval Augmented Prompt for Low-Resource Languages","created":"2022-12-19","cited_by_count":17,"area":"rag"},{"id":"2203.14655","title":"Few-Shot Learning with Siamese Networks and Label Tuning","created":"2022-03-28","cited_by_count":15,"area":null},{"id":"2206.07808","title":"Alexa Teacher Model: Pretraining and Distilling Multi-Billion-Parameter Encoders for Natural Language Understanding Systems","created":"2022-06-15","cited_by_count":15,"area":"distill"},{"id":"2310.19240","title":"M4LE: A Multi-Ability Multi-Range Multi-Task Multi-Domain Long-Context Evaluation Benchmark for Large Language Models","created":"2023-10-30","cited_by_count":15,"area":null},{"id":"2305.11790","title":"Prompting with Pseudo-Code Instructions","created":"2023-05-19","cited_by_count":14,"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":"2311.08273","title":"Examining Modularity in Multilingual LMs via Language-Specialized Subnetworks","created":"2023-11-14","cited_by_count":13,"area":null},{"id":"2403.15484","title":"RakutenAI-7B: Extending Large Language Models for Japanese","created":"2024-03-21","cited_by_count":13,"area":null},{"id":"2209.13773","title":"METS-CoV: A Dataset of Medical Entity and Targeted Sentiment on COVID-19 Related Tweets","created":"2022-09-28","cited_by_count":12,"area":null},{"id":"2403.06414","title":"Evolving Knowledge Distillation with Large Language Models and Active Learning","created":"2024-03-11","cited_by_count":12,"area":"distill"},{"id":"2204.09347","title":"Active Few-Shot Learning with FASL","created":"2022-04-20","cited_by_count":11,"area":null},{"id":"2407.12813","title":"Data Generation Using Large Language Models for Text Classification: An Empirical Case Study","created":"2024-06-27","cited_by_count":11,"area":null},{"id":"2506.01435","title":"Redundancy, Isotropy, and Intrinsic Dimensionality of Prompt-based Text Embeddings","created":"2025-06-02","cited_by_count":11,"area":null},{"id":"2306.07902","title":"Massively Multilingual Corpus of Sentiment Datasets and Multi-faceted Sentiment Classification Benchmark","created":"2023-06-13","cited_by_count":10,"area":null},{"id":"2406.04215","title":"mCSQA: Multilingual Commonsense Reasoning Dataset with Unified Creation Strategy by Language Models and Humans","created":"2024-06-06","cited_by_count":10,"area":"lr"},{"id":"2106.09462","title":"pysentimiento: A Python Toolkit for Opinion Mining and Social NLP tasks","created":"2021-06-17","cited_by_count":9,"area":null},{"id":"2210.16656","title":"Auxo: Efficient Federated Learning via Scalable Client Clustering","created":"2022-10-29","cited_by_count":8,"area":null},{"id":"2303.00721","title":"Bootstrapping Parallel Anchors for Relative Representations","created":"2023-03-01","cited_by_count":8,"area":null},{"id":"2305.07491","title":"A Comprehensive Analysis of Adapter Efficiency","created":"2023-05-12","cited_by_count":8,"area":null},{"id":"2305.11673","title":"Bias Beyond English: Counterfactual Tests for Bias in Sentiment Analysis in Four Languages","created":"2023-05-19","cited_by_count":8,"area":null},{"id":"2412.19037","title":"CL-Attack: Textual Backdoor Attacks via Cross-Lingual Triggers","created":"2024-12-26","cited_by_count":8,"area":"safety"},{"id":"2505.16538","title":"Mechanistic Understanding and Mitigation of Language Confusion in English-Centric Large Language Models","created":"2025-05-22","cited_by_count":8,"area":null},{"id":"2508.17744","title":"Randomly Removing 50% of Dimensions in Text Embeddings has Minimal Impact on Retrieval and Classification Tasks","created":"2025-08-25","cited_by_count":8,"area":null},{"id":"2210.13838","title":"Multilingual Relation Classification via Efficient and Effective Prompting","created":"2022-10-25","cited_by_count":7,"area":null},{"id":"2307.07880","title":"Is Prompt-Based Finetuning Always Better than Vanilla Finetuning? Insights from Cross-Lingual Language Understanding","created":"2023-07-15","cited_by_count":7,"area":null},{"id":"2311.09404","title":"To Translate or Not to Translate: A Systematic Investigation of Translation-Based Cross-Lingual Transfer to Low-Resource Languages","created":"2023-11-15","cited_by_count":7,"area":null},{"id":"2401.16589","title":"ToPro: Token-Level Prompt Decomposition for Cross-Lingual Sequence Labeling Tasks","created":"2024-01-29","cited_by_count":7,"area":null},{"id":"2402.13016","title":"Understanding the effects of language-specific class imbalance in multilingual fine-tuning","created":"2024-02-20","cited_by_count":7,"area":null},{"id":"2408.12263","title":"Toward the Evaluation of Large Language Models Considering Score Variance across Instruction Templates","created":"2024-08-22","cited_by_count":7,"area":null},{"id":"2204.00791","title":"CL-XABSA: Contrastive Learning for Cross-lingual Aspect-based Sentiment Analysis","created":"2022-04-02","cited_by_count":6,"area":null},{"id":"2204.14264","title":"Polyglot Prompt: Multilingual Multitask PrompTraining","created":"2022-04-29","cited_by_count":6,"area":null},{"id":"2210.09588","title":"Synergy with Translation Artifacts for Training and Inference in Multilingual Tasks","created":"2022-10-18","cited_by_count":6,"area":null},{"id":"2212.02924","title":"Controlled Text Generation using T5 based Encoder-Decoder Soft Prompt Tuning and Analysis of the Utility of Generated Text in AI","created":"2022-12-06","cited_by_count":6,"area":null},{"id":"2306.09308","title":"Matching Pairs: Attributing Fine-Tuned Models to their Pre-Trained Large Language Models","created":"2023-06-15","cited_by_count":6,"area":null},{"id":"2403.12809","title":"Comparing Explanation Faithfulness between Multilingual and Monolingual Fine-tuned Language Models","created":"2024-03-19","cited_by_count":6,"area":null},{"id":"2502.18782","title":"Active Few-Shot Learning for Text Classification","created":"2025-02-26","cited_by_count":6,"area":null},{"id":"2505.11665","title":"Multilingual Prompt Engineering in Large Language Models: A Survey Across NLP Tasks","created":"2025-05-16","cited_by_count":6,"area":null},{"id":"2507.13236","title":"Enhancing Cross-task Transfer of Large Language Models via Activation Steering","created":"2025-07-17","cited_by_count":6,"area":"mechinterp"},{"id":"2201.02026","title":"Fortunately, Discourse Markers Can Enhance Language Models for Sentiment Analysis","created":"2022-01-06","cited_by_count":5,"area":null},{"id":"2210.09773","title":"Retrofitting Multilingual Sentence Embeddings with Abstract Meaning Representation","created":"2022-10-18","cited_by_count":5,"area":null},{"id":"2309.03412","title":"From Base to Conversational: Japanese Instruction Dataset and Tuning Large Language Models","created":"2023-09-07","cited_by_count":5,"area":null},{"id":"2402.11469","title":"A Curious Case of Searching for the Correlation between Training Data and Adversarial Robustness of Transformer Textual Models","created":"2024-02-18","cited_by_count":5,"area":null},{"id":"2407.01091","title":"M2QA: Multi-domain Multilingual Question Answering","created":"2024-07-01","cited_by_count":5,"area":null},{"id":"2409.18461","title":"Towards Diverse Device Heterogeneous Federated Learning via Task Arithmetic Knowledge Integration","created":"2024-09-27","cited_by_count":5,"area":null},{"id":"2410.02472","title":"Meta-Models: An Architecture for Decoding LLM Behaviors Through Interpreted Embeddings and Natural Language","created":"2024-10-03","cited_by_count":5,"area":null},{"id":"2310.13998","title":"Transductive Learning for Textual Few-Shot Classification in API-based Embedding Models","created":"2023-10-21","cited_by_count":4,"area":null},{"id":"2409.10967","title":"Relative Representations: Topological and Geometric Perspectives","created":"2024-09-17","cited_by_count":4,"area":null},{"id":"2503.15222","title":"Model Hubs and Beyond: Analyzing Model Popularity, Performance, and Documentation","created":"2025-03-19","cited_by_count":4,"area":null},{"id":"2509.12892","title":"Conan-Embedding-v2: Training an LLM from Scratch for Text Embeddings","created":"2025-09-16","cited_by_count":4,"area":null},{"id":"2202.13654","title":"Cross-Lingual Text Classification with Multilingual Distillation and Zero-Shot-Aware Training","created":"2022-02-28","cited_by_count":3,"area":null},{"id":"2204.04937","title":"Assessment of Massively Multilingual Sentiment Classifiers","created":"2022-04-11","cited_by_count":3,"area":null},{"id":"2301.04761","title":"NarrowBERT: Accelerating Masked Language Model Pretraining and Inference","created":"2023-01-11","cited_by_count":3,"area":null},{"id":"2301.09753","title":"Towards Modular Machine Learning Solution Development: Benefits and Trade-offs","created":"2023-01-23","cited_by_count":3,"area":null},{"id":"2305.12709","title":"Cross-lingual Transfer Can Worsen Bias in Sentiment Analysis","created":"2023-05-22","cited_by_count":3,"area":null},{"id":"2501.07111","title":"ListConRanker: A Contrastive Text Reranker with Listwise Encoding","created":"2025-01-13","cited_by_count":3,"area":"rag"},{"id":"2211.14865","title":"Understanding BLOOM: An empirical study on diverse NLP tasks","created":"2022-11-27","cited_by_count":2,"area":null},{"id":"2305.17197","title":"Entailment as Robust Self-Learner","created":"2023-05-26","cited_by_count":2,"area":null},{"id":"2310.05069","title":"Unleashing the Multilingual Encoder Potential: Boosting Zero-Shot Performance via Probability Calibration","created":"2023-10-08","cited_by_count":2,"area":null},{"id":"2310.14849","title":"Universal Domain Adaptation for Robust Handling of Distributional Shifts in NLP","created":"2023-10-23","cited_by_count":2,"area":null},{"id":"2311.06549","title":"Zero-Shot Cross-Lingual Sentiment Classification under Distribution Shift: an Exploratory Study","created":"2023-11-11","cited_by_count":2,"area":null},{"id":"2312.09718","title":"Discovering Highly Influential Shortcut Reasoning: An Automated Template-Free Approach","created":"2023-12-15","cited_by_count":2,"area":null},{"id":"2401.04821","title":"MoSECroT: Model Stitching with Static Word Embeddings for Crosslingual Zero-shot Transfer","created":"2024-01-09","cited_by_count":2,"area":null},{"id":"2402.03142","title":"Less is KEN: a Universal and Simple Non-Parametric Pruning Algorithm for Large Language Models","created":"2024-02-05","cited_by_count":2,"area":null},{"id":"2404.01706","title":"Polarity Calibration for Opinion Summarization","created":"2024-04-02","cited_by_count":2,"area":null},{"id":"2404.13906","title":"Generating Attractive and Authentic Copywriting from Customer Reviews","created":"2024-04-22","cited_by_count":2,"area":null},{"id":"2405.11775","title":"Exploring Ordinality in Text Classification: A Comparative Study of Explicit and Implicit Techniques","created":"2024-05-20","cited_by_count":2,"area":null},{"id":"2409.16911","title":"Pruning Multilingual Large Language Models for Multilingual Inference","created":"2024-09-25","cited_by_count":2,"area":null},{"id":"2412.13161","title":"BanglishRev: A Large-Scale Bangla-English and Code-mixed Dataset of Product Reviews in E-Commerce","created":"2024-12-17","cited_by_count":2,"area":null},{"id":"2412.18053","title":"Neuron Empirical Gradient: Discovering and Quantifying Neurons Global Linear Controllability","created":"2024-12-24","cited_by_count":2,"area":null}],"next_cursor":"100"}