{"total":128,"rows":[{"id":"2111.09543","title":"DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing","created":"2021-11-18","cited_by_count":1254,"area":null},{"id":"2212.03533","title":"Text Embeddings by Weakly-Supervised Contrastive Pre-training","created":"2022-12-07","cited_by_count":1253,"area":null},{"id":"2402.05672","title":"Multilingual E5 Text Embeddings: A Technical Report","created":"2024-02-08","cited_by_count":372,"area":null},{"id":"2207.00112","title":"Language model compression with weighted low-rank factorization","created":"2022-06-30","cited_by_count":195,"area":null},{"id":"2204.06487","title":"Adapting Pre-trained Language Models to African Languages via Multilingual Adaptive Fine-Tuning","created":"2022-04-13","cited_by_count":149,"area":null},{"id":"2103.13076","title":"Finetuning Pretrained Transformers into RNNs","created":"2021-03-24","cited_by_count":96,"area":null},{"id":"2210.01351","title":"Less is More: Task-aware Layer-wise Distillation for Language Model Compression","created":"2022-10-04","cited_by_count":93,"area":null},{"id":"2204.07154","title":"MiniViT: Compressing Vision Transformers with Weight Multiplexing","created":"2022-04-14","cited_by_count":88,"area":null},{"id":"2410.10700","title":"LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution Shifts","created":"2024-10-14","cited_by_count":86,"area":null},{"id":"2405.05374","title":"Arctic-Embed: Scalable, Efficient, and Accurate Text Embedding Models","created":"2024-05-08","cited_by_count":61,"area":null},{"id":"2203.07228","title":"FairLex: A Multilingual Benchmark for Evaluating Fairness in Legal Text Processing","created":"2022-03-14","cited_by_count":49,"area":null},{"id":"2112.12731","title":"ERNIE 3.0 Titan: Exploring Larger-scale Knowledge Enhanced Pre-training for Language Understanding and Generation","created":"2021-12-23","cited_by_count":46,"area":null},{"id":"2202.07105","title":"A Survey on Model Compression and Acceleration for Pretrained Language Models","created":"2022-02-15","cited_by_count":45,"area":null},{"id":"2304.06845","title":"SemEval-2023 Task 12: Sentiment Analysis for African Languages (AfriSenti-SemEval)","created":"2023-04-13","cited_by_count":41,"area":null},{"id":"2510.06377","title":"Relational Transformer: Toward Zero-Shot Foundation Models for Relational Data","created":"2025-10-07","cited_by_count":39,"area":null},{"id":"2303.00807","title":"UDAPDR: Unsupervised Domain Adaptation via LLM Prompting and Distillation of Rerankers","created":"2023-03-01","cited_by_count":37,"area":null},{"id":"2205.14443","title":"A Closer Look at Self-Supervised Lightweight Vision Transformers","created":"2022-05-28","cited_by_count":31,"area":null},{"id":"2305.13808","title":"Asking Clarification Questions to Handle Ambiguity in Open-Domain QA","created":"2023-05-23","cited_by_count":26,"area":null},{"id":"2406.02396","title":"The Scandinavian Embedding Benchmarks: Comprehensive Assessment of Multilingual and Monolingual Text Embedding","created":"2024-06-04","cited_by_count":26,"area":null},{"id":"2304.04280","title":"FrenchMedMCQA: A French Multiple-Choice Question Answering Dataset for Medical domain","created":"2023-04-09","cited_by_count":25,"area":null},{"id":"2505.23628","title":"AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corpora","created":"2025-05-29","cited_by_count":23,"area":null},{"id":"2112.08723","title":"Distilled Dual-Encoder Model for Vision-Language Understanding","created":"2021-12-16","cited_by_count":22,"area":null},{"id":"2211.17148","title":"ConvLab-3: A Flexible Dialogue System Toolkit Based on a Unified Data Format","created":"2022-11-30","cited_by_count":22,"area":null},{"id":"2302.14771","title":"Generic-to-Specific Distillation of Masked Autoencoders","created":"2023-02-28","cited_by_count":19,"area":null},{"id":"2406.01607","title":"Recent advances in text embedding: A Comprehensive Review of Top-Performing Methods on the MTEB Benchmark","created":"2024-05-27","cited_by_count":19,"area":null},{"id":"2403.10144","title":"NLP Verification: Towards a General Methodology for Certifying Robustness","created":"2024-03-15","cited_by_count":16,"area":null},{"id":"2409.07691","title":"Enhancing Q&A Text Retrieval with Ranking Models: Benchmarking, fine-tuning and deploying Rerankers for RAG","created":"2024-09-12","cited_by_count":16,"area":null},{"id":"2401.15347","title":"A Comprehensive Survey of Compression Algorithms for Language Models","created":"2024-01-27","cited_by_count":15,"area":null},{"id":"2404.09296","title":"Cross-Data Knowledge Graph Construction for LLM-enabled Educational Question-Answering System: A Case Study at HCMUT","created":"2024-04-14","cited_by_count":14,"area":null},{"id":"2511.20030","title":"Cross-Contrastive Clustering for Multimodal Attributed Graphs with Dual Graph Filtering","created":"2025-11-25","cited_by_count":14,"area":null},{"id":"2603.01990","title":"According to Me: Long-Term Personalized Referential Memory QA","created":"2026-03-02","cited_by_count":14,"area":null},{"id":"2211.17135","title":"BudgetLongformer: Can we Cheaply Pretrain a SotA Legal Language Model From Scratch?","created":"2022-11-30","cited_by_count":13,"area":null},{"id":"2304.05659","title":"RIFormer: Keep Your Vision Backbone Effective While Removing Token Mixer","created":"2023-04-12","cited_by_count":13,"area":null},{"id":"2308.05502","title":"Bringing order into the realm of Transformer-based language models for artificial intelligence and law","created":"2023-08-10","cited_by_count":13,"area":null},{"id":"2309.05015","title":"DeViT: Decomposing Vision Transformers for Collaborative Inference in Edge Devices","created":"2023-09-10","cited_by_count":13,"area":null},{"id":"2106.00219","title":"Question-aware Transformer Models for Consumer Health Question Summarization","created":"2021-06-01","cited_by_count":11,"area":null},{"id":"2306.14152","title":"Low-Rank Prune-And-Factorize for Language Model Compression","created":"2023-06-25","cited_by_count":11,"area":null},{"id":"2411.06171","title":"SEEKR: Selective Attention-Guided Knowledge Retention for Continual Learning of Large Language Models","created":"2024-11-09","cited_by_count":11,"area":null},{"id":"2303.14334","title":"The Semantic Reader Project: Augmenting Scholarly Documents through AI-Powered Interactive Reading Interfaces","created":"2023-03-25","cited_by_count":9,"area":null},{"id":"2506.12473","title":"TagRouter: Learning Route to LLMs through Tags for Open-Domain Text Generation Tasks","created":"2025-06-14","cited_by_count":9,"area":null},{"id":"2202.08316","title":"FAMIE: A Fast Active Learning Framework for Multilingual Information Extraction","created":"2022-02-16","cited_by_count":8,"area":null},{"id":"2309.11593","title":"Sentence Attention Blocks for Answer Grounding","created":"2023-09-20","cited_by_count":8,"area":null},{"id":"2410.09982","title":"Self-Data Distillation for Recovering Quality in Pruned Large Language Models","created":"2024-10-13","cited_by_count":8,"area":null},{"id":"2411.12174","title":"Just KIDDIN: Knowledge Infusion and Distillation for Detection of INdecent Memes","created":"2024-11-19","cited_by_count":8,"area":null},{"id":"2502.20204","title":"Granite Embedding Models","created":"2025-02-27","cited_by_count":8,"area":null},{"id":"2310.10054","title":"NASH: A Simple Unified Framework of Structured Pruning for Accelerating Encoder-Decoder Language Models","created":"2023-10-16","cited_by_count":7,"area":null},{"id":"2311.00447","title":"On the Opportunities of Green Computing: A Survey","created":"2023-11-01","cited_by_count":7,"area":null},{"id":"2401.01943","title":"Generalist embedding models are better at short-context clinical semantic search than specialized embedding models","created":"2024-01-03","cited_by_count":7,"area":null},{"id":"2402.03223","title":"English Prompts are Better for NLI-based Zero-Shot Emotion Classification than Target-Language Prompts","created":"2024-02-05","cited_by_count":7,"area":null},{"id":"2402.15059","title":"ColBERT-XM: A Modular Multi-Vector Representation Model for Zero-Shot Multilingual Information Retrieval","created":"2024-02-23","cited_by_count":7,"area":null},{"id":"2204.02922","title":"Paying More Attention to Self-attention: Improving Pre-trained Language Models via Attention Guiding","created":"2022-04-06","cited_by_count":6,"area":null},{"id":"2306.01709","title":"Distilling Efficient Language-Specific Models for Cross-Lingual Transfer","created":"2023-06-02","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":"2306.13114","title":"A Reference-less Quality Metric for Automatic Speech Recognition via Contrastive-Learning of a Multi-Language Model with Self-Supervision","created":"2023-06-21","cited_by_count":6,"area":null},{"id":"2310.08797","title":"A Comparative Analysis of Task-Agnostic Distillation Methods for Compressing Transformer Language Models","created":"2023-10-13","cited_by_count":6,"area":null},{"id":"2312.04720","title":"From Big to Small Without Losing It All: Text Augmentation with ChatGPT for Efficient Sentiment Analysis","created":"2023-12-07","cited_by_count":6,"area":null},{"id":"2312.06147","title":"\"What's important here?\": Opportunities and Challenges of Using LLMs in Retrieving Information from Web Interfaces","created":"2023-12-11","cited_by_count":6,"area":null},{"id":"2405.10725","title":"INDUS: Effective and Efficient Language Models for Scientific Applications","created":"2024-05-17","cited_by_count":6,"area":null},{"id":"2509.22075","title":"CoSpaDi: Compressing LLMs via Calibration-Guided Sparse Dictionary Learning","created":"2025-09-26","cited_by_count":6,"area":null},{"id":"2205.14570","title":"MiniDisc: Minimal Distillation Schedule for Language Model Compression","created":"2022-05-29","cited_by_count":5,"area":null},{"id":"2207.04993","title":"Embedding Recycling for Language Models","created":"2022-07-11","cited_by_count":5,"area":null},{"id":"2210.13016","title":"Cards Against AI: Predicting Humor in a Fill-in-the-blank Party Game","created":"2022-10-24","cited_by_count":5,"area":null},{"id":"2306.00014","title":"PreQuant: A Task-agnostic Quantization Approach for Pre-trained Language Models","created":"2023-05-30","cited_by_count":5,"area":null},{"id":"2410.00362","title":"FedPT: Federated Proxy-Tuning of Large Language Models on Resource-Constrained Edge Devices","created":"2024-10-01","cited_by_count":5,"area":null},{"id":"2502.10433","title":"Neural Genetic Search in Discrete Spaces","created":"2025-02-09","cited_by_count":5,"area":null},{"id":"2209.09593","title":"EffEval: A Comprehensive Evaluation of Efficiency for MT Evaluation Metrics","created":"2022-09-20","cited_by_count":4,"area":null},{"id":"2305.12330","title":"Task-agnostic Distillation of Encoder-Decoder Language Models","created":"2023-05-21","cited_by_count":4,"area":null},{"id":"2306.12577","title":"NoRefER: a Referenceless Quality Metric for Automatic Speech Recognition via Semi-Supervised Language Model Fine-Tuning with Contrastive Learning","created":"2023-06-21","cited_by_count":4,"area":null},{"id":"2312.11344","title":"Muted: Multilingual Targeted Offensive Speech Identification and Visualization","created":"2023-12-18","cited_by_count":4,"area":null},{"id":"2401.11268","title":"Word-Level ASR Quality Estimation for Efficient Corpus Sampling and Post-Editing through Analyzing Attentions of a Reference-Free Metric","created":"2024-01-20","cited_by_count":4,"area":null},{"id":"2404.12210","title":"An Experimental Study on Exploring Strong Lightweight Vision Transformers via Masked Image Modeling Pre-Training","created":"2024-04-18","cited_by_count":4,"area":null},{"id":"2406.15231","title":"Synthetic Lyrics Detection Across Languages and Genres","created":"2024-06-21","cited_by_count":4,"area":null},{"id":"2512.13733","title":"Low-Rank Compression of Language Models via Differentiable Rank Selection","created":"2025-12-14","cited_by_count":4,"area":null},{"id":"2310.15594","title":"Retrieval-based Knowledge Transfer: An Effective Approach for Extreme Large Language Model Compression","created":"2023-10-24","cited_by_count":3,"area":null},{"id":"2406.05276","title":"VTrans: Accelerating Transformer Compression with Variational Information Bottleneck based Pruning","created":"2024-06-07","cited_by_count":3,"area":null},{"id":"2407.05463","title":"Training Task Experts through Retrieval Based Distillation","created":"2024-07-07","cited_by_count":3,"area":null},{"id":"2408.04998","title":"ProFuser: Progressive Fusion of Large Language Models","created":"2024-08-09","cited_by_count":3,"area":null},{"id":"2408.15261","title":"Civiverse: A Dataset for Analyzing User Engagement with Open-Source Text-to-Image Models","created":"2024-08-10","cited_by_count":3,"area":null},{"id":"2506.15981","title":"Double Entendre: Robust Audio-Based AI-Generated Lyrics Detection via Multi-View Fusion","created":"2025-06-19","cited_by_count":3,"area":null},{"id":"2509.22506","title":"Representing LLMs in Prompt Semantic Task Space","created":"2025-09-26","cited_by_count":3,"area":null},{"id":"2305.15904","title":"MTCue: Learning Zero-Shot Control of Extra-Textual Attributes by Leveraging Unstructured Context in Neural Machine Translation","created":"2023-05-25","cited_by_count":2,"area":null},{"id":"2403.15744","title":"On the Fragility of Active Learners for Text Classification","created":"2024-03-23","cited_by_count":2,"area":null},{"id":"2406.03757","title":"RoboCoder: Robotic Learning from Basic Skills to General Tasks with Large Language Models","created":"2024-06-06","cited_by_count":2,"area":null},{"id":"2508.20353","title":"DFAMS: Dynamic-flow guided Federated Alignment based Multi-prototype Search","created":"2025-08-28","cited_by_count":2,"area":null},{"id":"2509.20677","title":"Stability of In-Context Learning: A Spectral Coverage Perspective","created":"2025-09-25","cited_by_count":2,"area":null},{"id":"2510.13998","title":"BitNet Distillation","created":"2025-10-15","cited_by_count":2,"area":null},{"id":"2210.17114","title":"QuaLA-MiniLM: a Quantized Length Adaptive MiniLM","created":"2022-10-31","cited_by_count":1,"area":null},{"id":"2211.15927","title":"Compressing Cross-Lingual Multi-Task Models at Qualtrics","created":"2022-11-29","cited_by_count":1,"area":null},{"id":"2302.11208","title":"KS-DETR: Knowledge Sharing in Attention Learning for Detection Transformer","created":"2023-02-22","cited_by_count":1,"area":null},{"id":"2309.01015","title":"MPTopic: Improving topic modeling via Masked Permuted pre-training","created":"2023-09-02","cited_by_count":1,"area":null},{"id":"2310.18366","title":"A Multilingual Virtual Guide for Self-Attachment Technique","created":"2023-10-25","cited_by_count":1,"area":null},{"id":"2410.11434","title":"Titanic Calling: Low Bandwidth Video Conference from the Titanic Wreck","created":"2024-10-15","cited_by_count":1,"area":null},{"id":"2507.01504","title":"Following the Clues: Experiments on Person Re-ID using Cross-Modal Intelligence","created":"2025-07-02","cited_by_count":1,"area":null},{"id":"2602.00942","title":"SALAAD: Sparse And Low-Rank Adaptation via ADMM for Large Language Model Inference","created":"2026-02-01","cited_by_count":1,"area":null},{"id":"2604.03172","title":"EffiMiniVLM: A Compact Dual-Encoder Regression Framework","created":"2026-04-03","cited_by_count":1,"area":null},{"id":"2604.22436","title":"AgentSearchBench: A Benchmark for AI Agent Search in the Wild","created":"2026-04-24","cited_by_count":1,"area":null},{"id":"2605.27345","title":"MATCHA: Matching Text via Contrastive Semantic Alignment","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2605.29522","title":"DeepSurvey: Agent-Oriented Automated Survey Generation with Analytical Depth and Citation Reliability","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2606.14929","title":"Policy Regret for Embedding Model Routing: Contextual Bandits with Low-Rank Experts","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2606.31796","title":"CHERRY: Compressed Hierarchical Experts with Recurrent Representational Yield","created":"2026-06-30","cited_by_count":1,"area":null}],"next_cursor":"100"}