{"total":361,"rows":[{"id":"2212.03533","title":"Text Embeddings by Weakly-Supervised Contrastive Pre-training","created":"2022-12-07","cited_by_count":1253,"area":null},{"id":"2308.03281","title":"Towards General Text Embeddings with Multi-stage Contrastive Learning","created":"2023-08-07","cited_by_count":723,"area":null},{"id":"2210.07316","title":"MTEB: Massive Text Embedding Benchmark","created":"2022-10-13","cited_by_count":640,"area":null},{"id":"2309.07597","title":"C-Pack: Packed Resources For General Chinese Embeddings","created":"2023-09-14","cited_by_count":578,"area":null},{"id":"2112.07899","title":"Large Dual Encoders Are Generalizable Retrievers","created":"2021-12-15","cited_by_count":456,"area":null},{"id":"2402.05672","title":"Multilingual E5 Text Embeddings: A Technical Report","created":"2024-02-08","cited_by_count":372,"area":null},{"id":"2212.09741","title":"One Embedder, Any Task: Instruction-Finetuned Text Embeddings","created":"2022-12-19","cited_by_count":333,"area":null},{"id":"2401.00368","title":"Improving Text Embeddings with Large Language Models","created":"2023-12-31","cited_by_count":303,"area":null},{"id":"2402.01613","title":"Nomic Embed: Training a Reproducible Long Context Text Embedder","created":"2024-02-02","cited_by_count":265,"area":null},{"id":"2202.06991","title":"Transformer Memory as a Differentiable Search Index","created":"2022-02-14","cited_by_count":247,"area":null},{"id":"2402.09906","title":"Generative Representational Instruction Tuning","created":"2024-02-15","cited_by_count":233,"area":null},{"id":"2305.05065","title":"Recommender Systems with Generative Retrieval","created":"2023-05-08","cited_by_count":198,"area":null},{"id":"2312.03718","title":"Large Language Models in Law: A Survey","created":"2023-11-26","cited_by_count":128,"area":null},{"id":"2210.10634","title":"RankT5: Fine-Tuning T5 for Text Ranking with Ranking Losses","created":"2022-10-12","cited_by_count":115,"area":null},{"id":"2503.07891","title":"Gemini Embedding: Generalizable Embeddings from Gemini","created":"2025-03-10","cited_by_count":94,"area":null},{"id":"2402.09668","title":"How to Train Data-Efficient LLMs","created":"2024-02-15","cited_by_count":93,"area":null},{"id":"2203.02167","title":"SimKGC: Simple Contrastive Knowledge Graph Completion with Pre-trained Language Models","created":"2022-03-04","cited_by_count":91,"area":null},{"id":"2412.08821","title":"Large Concept Models: Language Modeling in a Sentence Representation Space","created":"2024-12-11","cited_by_count":89,"area":null},{"id":"2409.19886","title":"RouterDC: Query-Based Router by Dual Contrastive Learning for Assembling Large Language Models","created":"2024-09-30","cited_by_count":88,"area":null},{"id":"2307.16645","title":"Scaling Sentence Embeddings with Large Language Models","created":"2023-07-31","cited_by_count":85,"area":null},{"id":"2403.20327","title":"Gecko: Versatile Text Embeddings Distilled from Large Language Models","created":"2024-03-29","cited_by_count":83,"area":null},{"id":"2305.03010","title":"Sentence Embedding Leaks More Information than You Expect: Generative Embedding Inversion Attack to Recover the Whole Sentence","created":"2023-05-04","cited_by_count":81,"area":null},{"id":"2302.03202","title":"Exploring the Benefits of Training Expert Language Models over Instruction Tuning","created":"2023-02-07","cited_by_count":80,"area":null},{"id":"2308.11131","title":"ReLLa: Retrieval-enhanced Large Language Models for Lifelong Sequential Behavior Comprehension in Recommendation","created":"2023-08-22","cited_by_count":77,"area":null},{"id":"2402.15449","title":"Repetition Improves Language Model Embeddings","created":"2024-02-23","cited_by_count":72,"area":null},{"id":"2305.14871","title":"ClusterLLM: Large Language Models as a Guide for Text Clustering","created":"2023-05-24","cited_by_count":70,"area":null},{"id":"2312.07661","title":"CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor","created":"2023-12-12","cited_by_count":69,"area":null},{"id":"2112.08558","title":"CONQRR: Conversational Query Rewriting for Retrieval with Reinforcement Learning","created":"2021-12-16","cited_by_count":68,"area":null},{"id":"2402.09997","title":"LoraRetriever: Input-Aware LoRA Retrieval and Composition for Mixed Tasks in the Wild","created":"2024-02-15","cited_by_count":68,"area":null},{"id":"2306.01684","title":"Harnessing large-language models to generate private synthetic text","created":"2023-06-02","cited_by_count":65,"area":null},{"id":"2205.09073","title":"Dialog Inpainting: Turning Documents into Dialogs","created":"2022-05-18","cited_by_count":56,"area":null},{"id":"2308.07968","title":"Teach LLMs to Personalize -- An Approach inspired by Writing Education","created":"2023-08-15","cited_by_count":48,"area":null},{"id":"2204.07447","title":"Stretching Sentence-pair NLI Models to Reason over Long Documents and Clusters","created":"2022-04-15","cited_by_count":44,"area":null},{"id":"2303.03363","title":"Enhancing Activity Prediction Models in Drug Discovery with the Ability to Understand Human Language","created":"2023-03-06","cited_by_count":44,"area":null},{"id":"2305.10847","title":"Large Language Models can be Guided to Evade AI-Generated Text Detection","created":"2023-05-18","cited_by_count":44,"area":null},{"id":"2402.02511","title":"PoCo: Policy Composition from and for Heterogeneous Robot Learning","created":"2024-02-04","cited_by_count":42,"area":null},{"id":"2407.11895","title":"OmniBind: Large-scale Omni Multimodal Representation via Binding Spaces","created":"2024-07-16","cited_by_count":39,"area":null},{"id":"2509.14252","title":"LLM-JEPA: Large Language Models Meet Joint Embedding Predictive Architectures","created":"2025-09-11","cited_by_count":38,"area":null},{"id":"2309.10952","title":"LMDX: Language Model-based Document Information Extraction and Localization","created":"2023-09-19","cited_by_count":37,"area":null},{"id":"2212.09744","title":"DSI++: Updating Transformer Memory with New Documents","created":"2022-12-19","cited_by_count":35,"area":null},{"id":"2307.11224","title":"Jina Embeddings: A Novel Set of High-Performance Sentence Embedding Models","created":"2023-07-20","cited_by_count":35,"area":null},{"id":"2311.08089","title":"Improving In-context Learning of Multilingual Generative Language Models with Cross-lingual Alignment","created":"2023-11-14","cited_by_count":33,"area":null},{"id":"2405.01745","title":"Large Language Models for UAVs: Current State and Pathways to the Future","created":"2024-05-02","cited_by_count":33,"area":null},{"id":"2306.03900","title":"Model Spider: Learning to Rank Pre-Trained Models Efficiently","created":"2023-06-06","cited_by_count":32,"area":null},{"id":"2412.12591","title":"LLMs are Also Effective Embedding Models: An In-depth Overview","created":"2024-12-17","cited_by_count":32,"area":null},{"id":"2403.13310","title":"A Semantic Search Engine for Mathlib4","created":"2024-03-20","cited_by_count":31,"area":null},{"id":"2201.12093","title":"PCL: Peer-Contrastive Learning with Diverse Augmentations for Unsupervised Sentence Embeddings","created":"2022-01-28","cited_by_count":29,"area":null},{"id":"2311.08788","title":"X-Eval: Generalizable Multi-aspect Text Evaluation via Augmented Instruction Tuning with Auxiliary Evaluation Aspects","created":"2023-11-15","cited_by_count":28,"area":null},{"id":"2401.04858","title":"User Embedding Model for Personalized Language Prompting","created":"2024-01-10","cited_by_count":28,"area":null},{"id":"2402.09642","title":"Answer is All You Need: Instruction-following Text Embedding via Answering the Question","created":"2024-02-15","cited_by_count":27,"area":null},{"id":"2402.03660","title":"On the Emergence of Cross-Task Linearity in the Pretraining-Finetuning Paradigm","created":"2024-02-06","cited_by_count":26,"area":null},{"id":"2404.03921","title":"Simple Techniques for Enhancing Sentence Embeddings in Generative Language Models","created":"2024-04-05","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":"2406.10280","title":"Transferable Embedding Inversion Attack: Uncovering Privacy Risks in Text Embeddings without Model Queries","created":"2024-06-12","cited_by_count":25,"area":null},{"id":"2210.05758","title":"Decoupled Context Processing for Context Augmented Language Modeling","created":"2022-10-11","cited_by_count":24,"area":null},{"id":"2310.19056","title":"MILL: Mutual Verification with Large Language Models for Zero-Shot Query Expansion","created":"2023-10-29","cited_by_count":23,"area":null},{"id":"2204.12785","title":"Plug-and-Play Adaptation for Continuously-updated QA","created":"2022-04-27","cited_by_count":21,"area":null},{"id":"2311.04335","title":"Sub-Sentence Encoder: Contrastive Learning of Propositional Semantic Representations","created":"2023-11-07","cited_by_count":20,"area":null},{"id":"2403.05303","title":"ACLSum: A New Dataset for Aspect-based Summarization of Scientific Publications","created":"2024-03-08","cited_by_count":20,"area":null},{"id":"2502.13081","title":"Personalized Image Generation with Deep Generative Models: A Decade Survey","created":"2025-02-18","cited_by_count":20,"area":null},{"id":"2202.07280","title":"Saving Dense Retriever from Shortcut Dependency in Conversational Search","created":"2022-02-15","cited_by_count":19,"area":null},{"id":"2204.07120","title":"Exploring Dual Encoder Architectures for Question Answering","created":"2022-04-14","cited_by_count":19,"area":null},{"id":"2210.16798","title":"Generate, Discriminate and Contrast: A Semi-Supervised Sentence Representation Learning Framework","created":"2022-10-30","cited_by_count":19,"area":null},{"id":"2305.14583","title":"Natural Language Decompositions of Implicit Content Enable Better Text Representations","created":"2023-05-23","cited_by_count":19,"area":null},{"id":"2311.04886","title":"SEMQA: Semi-Extractive Multi-Source Question Answering","created":"2023-11-08","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":"2512.00565","title":"Describe Anything Anywhere At Any Moment","created":"2025-11-29","cited_by_count":19,"area":null},{"id":"2301.12473","title":"Large Language Models for Biomedical Knowledge Graph Construction: Information extraction from EMR notes","created":"2023-01-29","cited_by_count":18,"area":null},{"id":"2305.03598","title":"NLI4CT: Multi-Evidence Natural Language Inference for Clinical Trial Reports","created":"2023-05-05","cited_by_count":18,"area":null},{"id":"2310.18348","title":"Meaning Representations from Trajectories in Autoregressive Models","created":"2023-10-23","cited_by_count":18,"area":null},{"id":"2411.18814","title":"Unifying Generative and Dense Retrieval for Sequential Recommendation","created":"2024-11-27","cited_by_count":18,"area":null},{"id":"2412.11556","title":"Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs","created":"2024-12-16","cited_by_count":18,"area":null},{"id":"2502.13581","title":"ActionPiece: Contextually Tokenizing Action Sequences for Generative Recommendation","created":"2025-02-19","cited_by_count":18,"area":null},{"id":"2310.04475","title":"Demystifying Embedding Spaces using Large Language Models","created":"2023-10-06","cited_by_count":17,"area":null},{"id":"2311.03057","title":"GLEN: Generative Retrieval via Lexical Index Learning","created":"2023-11-06","cited_by_count":17,"area":null},{"id":"2402.18458","title":"Meta-Task Prompting Elicits Embeddings from Large Language Models","created":"2024-02-28","cited_by_count":16,"area":null},{"id":"2407.20243","title":"Matryoshka-Adaptor: Unsupervised and Supervised Tuning for Smaller Embedding Dimensions","created":"2024-07-17","cited_by_count":16,"area":null},{"id":"2410.00903","title":"Causal Inference with Generative Artificial Intelligence: Application to Texts as Treatments","created":"2024-10-01","cited_by_count":16,"area":null},{"id":"2304.11434","title":"L3Cube-IndicSBERT: A simple approach for learning cross-lingual sentence representations using multilingual BERT","created":"2023-04-22","cited_by_count":15,"area":null},{"id":"2312.04440","title":"OpenAsp: A Benchmark for Multi-document Open Aspect-based Summarization","created":"2023-12-07","cited_by_count":15,"area":null},{"id":"2402.01874","title":"The RL/LLM Taxonomy Tree: Reviewing Synergies Between Reinforcement Learning and Large Language Models","created":"2024-02-02","cited_by_count":15,"area":null},{"id":"2402.17327","title":"Data-Efficient Learning via Clustering-Based Sensitivity Sampling: Foundation Models and Beyond","created":"2024-02-27","cited_by_count":15,"area":null},{"id":"2412.01876","title":"Understanding Bias in Large-Scale Visual Datasets","created":"2024-12-02","cited_by_count":15,"area":null},{"id":"2305.14926","title":"Universal Self-Adaptive Prompting","created":"2023-05-24","cited_by_count":14,"area":null},{"id":"2402.15810","title":"OAG-Bench: A Human-Curated Benchmark for Academic Graph Mining","created":"2024-02-24","cited_by_count":14,"area":null},{"id":"2403.02694","title":"MeanCache: User-Centric Semantic Caching for LLM Web Services","created":"2024-03-05","cited_by_count":14,"area":null},{"id":"2408.00960","title":"PERSOMA: PERsonalized SOft ProMpt Adapter Architecture for Personalized Language Prompting","created":"2024-08-02","cited_by_count":14,"area":null},{"id":"2509.01907","title":"RSCC: A Large-Scale Remote Sensing Change Caption Dataset for Disaster Events","created":"2025-09-02","cited_by_count":14,"area":null},{"id":"2205.12078","title":"GraphQ IR: Unifying the Semantic Parsing of Graph Query Languages with One Intermediate Representation","created":"2022-05-24","cited_by_count":13,"area":null},{"id":"2206.10668","title":"BenchCLAMP: A Benchmark for Evaluating Language Models on Syntactic and Semantic Parsing","created":"2022-06-21","cited_by_count":13,"area":null},{"id":"2401.02709","title":"German Text Embedding Clustering Benchmark","created":"2024-01-05","cited_by_count":13,"area":null},{"id":"2403.00998","title":"Predictions from language models for multiple-choice tasks are not robust under variation of scoring methods","created":"2024-03-01","cited_by_count":13,"area":null},{"id":"2404.04163","title":"Dwell in the Beginning: How Language Models Embed Long Documents for Dense Retrieval","created":"2024-04-05","cited_by_count":13,"area":null},{"id":"2405.12368","title":"Layout Agnostic Human Activity Recognition in Smart Homes through Textual Descriptions Of Sensor Triggers (TDOST)","created":"2024-05-20","cited_by_count":13,"area":null},{"id":"2406.03151","title":"Which Side Are You On? A Multi-task Dataset for End-to-End Argument Summarisation and Evaluation","created":"2024-06-05","cited_by_count":13,"area":null},{"id":"2505.12831","title":"Contrastive Prompting Enhances Sentence Embeddings in LLMs through Inference-Time Steering","created":"2025-05-19","cited_by_count":13,"area":null},{"id":"2305.12641","title":"A Comprehensive Survey of Sentence Representations: From the BERT Epoch to the ChatGPT Era and Beyond","created":"2023-05-22","cited_by_count":12,"area":null},{"id":"2310.07023","title":"Automatic Macro Mining from Interaction Traces at Scale","created":"2023-10-10","cited_by_count":12,"area":null},{"id":"2501.01808","title":"MoEE: Mixture of Emotion Experts for Audio-Driven Portrait Animation","created":"2025-01-03","cited_by_count":12,"area":null},{"id":"2305.06300","title":"Evaluating Embedding APIs for Information Retrieval","created":"2023-05-10","cited_by_count":11,"area":null}],"next_cursor":"100"}