{"total":60,"rows":[{"id":"2402.03216","title":"M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation","created":"2024-02-05","cited_by_count":1073,"area":"distill"},{"id":"2309.07597","title":"C-Pack: Packed Resources For General Chinese Embeddings","created":"2023-09-14","cited_by_count":578,"area":null},{"id":"2404.05961","title":"LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders","created":"2024-04-09","cited_by_count":404,"area":null},{"id":"2401.00368","title":"Improving Text Embeddings with Large Language Models","created":"2023-12-31","cited_by_count":303,"area":null},{"id":"2407.19669","title":"mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval","created":"2024-07-29","cited_by_count":236,"area":null},{"id":"2402.09906","title":"Generative Representational Instruction Tuning","created":"2024-02-15","cited_by_count":233,"area":null},{"id":"2409.15700","title":"Making Text Embedders Few-Shot Learners","created":"2024-09-24","cited_by_count":79,"area":null},{"id":"2504.20595","title":"ReasonIR: Training Retrievers for Reasoning Tasks","created":"2025-04-29","cited_by_count":77,"area":"lr"},{"id":"2402.15449","title":"Repetition Improves Language Model Embeddings","created":"2024-02-23","cited_by_count":72,"area":null},{"id":"2304.11370","title":"SAILER: Structure-aware Pre-trained Language Model for Legal Case Retrieval","created":"2023-04-22","cited_by_count":62,"area":null},{"id":"2412.17259","title":"LegalAgentBench: Evaluating LLM Agents in Legal Domain","created":"2024-12-23","cited_by_count":59,"area":"agents"},{"id":"2310.07289","title":"Beyond Factuality: A Comprehensive Evaluation of Large Language Models as Knowledge Generators","created":"2023-10-11","cited_by_count":43,"area":null},{"id":"2310.17609","title":"LeCaRDv2: A Large-Scale Chinese Legal Case Retrieval Dataset","created":"2023-10-26","cited_by_count":38,"area":null},{"id":"2409.20288","title":"LexEval: A Comprehensive Chinese Legal Benchmark for Evaluating Large Language Models","created":"2024-09-30","cited_by_count":37,"area":null},{"id":"2506.20923","title":"KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Model","created":"2025-06-26","cited_by_count":36,"area":null},{"id":"2410.15393","title":"CalibraEval: Calibrating Prediction Distribution to Mitigate Selection Bias in LLMs-as-Judges","created":"2024-10-20","cited_by_count":34,"area":null},{"id":"2311.09198","title":"Never Lost in the Middle: Mastering Long-Context Question Answering with Position-Agnostic Decompositional Training","created":"2023-11-15","cited_by_count":32,"area":null},{"id":"2403.18684","title":"Scaling Laws For Dense Retrieval","created":"2024-03-27","cited_by_count":29,"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":"2502.20640","title":"LexRAG: Benchmarking Retrieval-Augmented Generation in Multi-Turn Legal Consultation Conversation","created":"2025-02-28","cited_by_count":19,"area":"rag"},{"id":"2305.06812","title":"THUIR@COLIEE 2023: Incorporating Structural Knowledge into Pre-trained Language Models for Legal Case Retrieval","created":"2023-05-11","cited_by_count":16,"area":null},{"id":"2304.11943","title":"Constructing Tree-based Index for Efficient and Effective Dense Retrieval","created":"2023-04-24","cited_by_count":15,"area":null},{"id":"2403.18365","title":"BLADE: Enhancing Black-box Large Language Models with Small Domain-Specific Models","created":"2024-03-27","cited_by_count":15,"area":null},{"id":"2603.19223","title":"F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World","created":"2026-03-19","cited_by_count":12,"area":null},{"id":"2305.06817","title":"THUIR@COLIEE 2023: More Parameters and Legal Knowledge for Legal Case Entailment","created":"2023-05-11","cited_by_count":11,"area":null},{"id":"2405.06932","title":"Piccolo2: General Text Embedding with Multi-task Hybrid Loss Training","created":"2024-05-11","cited_by_count":10,"area":null},{"id":"2403.18435","title":"DELTA: Pre-train a Discriminative Encoder for Legal Case Retrieval via Structural Word Alignment","created":"2024-03-27","cited_by_count":9,"area":null},{"id":"2510.00671","title":"Milco: Learned Sparse Retrieval Across Languages via a Multilingual Connector","created":"2025-10-01","cited_by_count":9,"area":null},{"id":"2502.20204","title":"Granite Embedding Models","created":"2025-02-27","cited_by_count":8,"area":null},{"id":"2410.14578","title":"Large Language Models Are Overparameterized Text Encoders","created":"2024-10-18","cited_by_count":6,"area":null},{"id":"2509.03020","title":"Training LLMs to be Better Text Embedders through Bidirectional Reconstruction","created":"2025-09-03","cited_by_count":6,"area":null},{"id":"2312.05669","title":"Relevance Feedback with Brain Signals","created":"2023-12-09","cited_by_count":4,"area":null},{"id":"2407.20207","title":"QAEA-DR: A Unified Text Augmentation Framework for Dense Retrieval","created":"2024-07-29","cited_by_count":4,"area":null},{"id":"2408.15491","title":"Enhancing and Accelerating Large Language Models via Instruction-Aware Contextual Compression","created":"2024-08-28","cited_by_count":4,"area":null},{"id":"2503.00501","title":"Qilin: A Multimodal Information Retrieval Dataset with APP-level User Sessions","created":"2025-03-01","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":"2501.07111","title":"ListConRanker: A Contrastive Text Reranker with Listwise Encoding","created":"2025-01-13","cited_by_count":3,"area":"rag"},{"id":"2507.20783","title":"On The Role of Pretrained Language Models in General-Purpose Text Embeddings: A Survey","created":"2025-07-28","cited_by_count":3,"area":null},{"id":"2511.17129","title":"Learning to Compress: Unlocking the Potential of Large Language Models for Text Representation","created":"2025-11-21","cited_by_count":3,"area":null},{"id":"2405.20994","title":"CWRCzech: 100M Query-Document Czech Click Dataset and Its Application to Web Relevance Ranking","created":"2024-05-31","cited_by_count":2,"area":null},{"id":"2507.19033","title":"SelfRACG: Enabling LLMs to Self-Express and Retrieve for Code Generation","created":"2025-07-25","cited_by_count":2,"area":"rag"},{"id":"2508.06781","title":"BiXSE: Improving Dense Retrieval via Probabilistic Graded Relevance Distillation","created":"2025-08-09","cited_by_count":2,"area":null},{"id":"2508.11442","title":"CoDiEmb: A Collaborative yet Distinct Framework for Unified Representation Learning in Information Retrieval and Semantic Textual Similarity","created":"2025-08-15","cited_by_count":2,"area":null},{"id":"2311.11691","title":"Towards Robust Text Retrieval with Progressive Learning","created":"2023-11-20","cited_by_count":1,"area":null},{"id":"2505.12260","title":"LightRetriever: A LLM-based Text Retrieval Architecture with Extremely Faster Query Inference","created":"2025-05-18","cited_by_count":1,"area":null},{"id":"2602.12783","title":"SQuTR: A Robustness Benchmark for Spoken Query to Text Retrieval under Acoustic Noise","created":"2026-02-13","cited_by_count":1,"area":null},{"id":"2610.05107","title":"SearchJev: A Fast and Calibrated System-1 Model for Search Agents","created":"2026-10-04","cited_by_count":1,"area":"agents"},{"id":"2507.20718","title":"Uncertainty-driven Embedding Convolution","created":"2025-07-28","cited_by_count":0,"area":null},{"id":"2507.23386","title":"Causal2Vec: Improving Decoder-only LLMs as Embedding Models through a Contextual Token","created":"2025-07-31","cited_by_count":0,"area":null},{"id":"2508.02222","title":"FinCPRG: A Bidirectional Generation Pipeline for Hierarchical Queries and Rich Relevance in Financial Chinese Passage Retrieval","created":"2025-08-04","cited_by_count":0,"area":null},{"id":"2509.09686","title":"GeoGPT-RAG Technical Report","created":"2025-08-18","cited_by_count":0,"area":null},{"id":"2512.13074","title":"A Simple and Effective Framework for Symmetric Consistent Indexing in Large-Scale Dense Retrieval","created":"2025-12-15","cited_by_count":0,"area":null},{"id":"2601.07861","title":"EmbeddingRWKV: State-Centric Retrieval with Reusable States","created":"2026-01-10","cited_by_count":0,"area":"rag"},{"id":"2601.21759","title":"Influence Guided Sampling for Domain Adaptation of Text Retrievers","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2602.05787","title":"Bagging-Based Model Merging for Robust General Text Embeddings","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2602.22221","title":"Evaluating Reliability Asymmetries in Chinese Factual Search and AI Answers","created":"2025-12-15","cited_by_count":0,"area":null},{"id":"2605.01372","title":"Embedding-based In-Context Prompt Training for Enhancing LLMs as Text Encoders","created":"2026-05-02","cited_by_count":0,"area":null},{"id":"2605.15081","title":"ML-Embed: Inclusive and Efficient Embeddings for a Multilingual World","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2606.22807","title":"Lychee-Reranker: Fast but Not Late Interaction for Compressed Document Reranking","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2609.36965","title":"Chinese-Jev: Bringing System One Model to Chinese-Language Tasks","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}