{"total":116,"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":"2304.09542","title":"Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents","created":"2023-04-19","cited_by_count":360,"area":"agents"},{"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":"2305.02156","title":"Zero-Shot Listwise Document Reranking with a Large Language Model","created":"2023-05-03","cited_by_count":82,"area":null},{"id":"2203.13357","title":"One Country, 700+ Languages: NLP Challenges for Underrepresented Languages and Dialects in Indonesia","created":"2022-03-24","cited_by_count":66,"area":null},{"id":"2210.09984","title":"Making a MIRACL: Multilingual Information Retrieval Across a Continuum of Languages","created":"2022-10-18","cited_by_count":47,"area":null},{"id":"2201.08471","title":"Transfer Learning Approaches for Building Cross-Language Dense Retrieval Models","created":"2022-01-20","cited_by_count":36,"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":"2401.07883","title":"The Chronicles of RAG: The Retriever, the Chunk and the Generator","created":"2024-01-15","cited_by_count":34,"area":"rag"},{"id":"2204.02363","title":"Towards Best Practices for Training Multilingual Dense Retrieval Models","created":"2022-04-05","cited_by_count":26,"area":null},{"id":"2408.16672","title":"Jina-ColBERT-v2: A General-Purpose Multilingual Late Interaction Retriever","created":"2024-08-29","cited_by_count":25,"area":null},{"id":"2311.05800","title":"Leveraging LLMs for Synthesizing Training Data Across Many Languages in Multilingual Dense Retrieval","created":"2023-11-10","cited_by_count":24,"area":null},{"id":"2407.13522","title":"INDIC QA BENCHMARK: A Multilingual Benchmark to Evaluate Question Answering capability of LLMs for Indic Languages","created":"2024-07-18","cited_by_count":24,"area":null},{"id":"2509.25085","title":"jina-reranker-v3: Last but Not Late Interaction for Listwise Document Reranking","created":"2025-09-29","cited_by_count":24,"area":null},{"id":"2401.04810","title":"Translate-Distill: Learning Cross-Language Dense Retrieval by Translation and Distillation","created":"2024-01-09","cited_by_count":22,"area":"distill"},{"id":"2209.01335","title":"Neural Approaches to Multilingual Information Retrieval","created":"2022-09-03","cited_by_count":18,"area":null},{"id":"2310.20158","title":"GAR-meets-RAG Paradigm for Zero-Shot Information Retrieval","created":"2023-10-31","cited_by_count":18,"area":null},{"id":"2204.02292","title":"Parameter-Efficient Neural Reranking for Cross-Lingual and Multilingual Retrieval","created":"2022-04-05","cited_by_count":17,"area":null},{"id":"2211.01482","title":"RQUGE: Reference-Free Metric for Evaluating Question Generation by Answering the Question","created":"2022-11-02","cited_by_count":17,"area":null},{"id":"2406.00231","title":"LLM-RankFusion: Mitigating Intrinsic Inconsistency in LLM-based Ranking","created":"2024-05-31","cited_by_count":16,"area":null},{"id":"2203.10232","title":"DuReader_retrieval: A Large-scale Chinese Benchmark for Passage Retrieval from Web Search Engine","created":"2022-03-19","cited_by_count":15,"area":null},{"id":"2301.12566","title":"Improving Cross-lingual Information Retrieval on Low-Resource Languages via Optimal Transport Distillation","created":"2023-01-29","cited_by_count":15,"area":null},{"id":"2305.19840","title":"BEIR-PL: Zero Shot Information Retrieval Benchmark for the Polish Language","created":"2023-05-31","cited_by_count":15,"area":null},{"id":"2407.20750","title":"JaColBERTv2.5: Optimising Multi-Vector Retrievers to Create State-of-the-Art Japanese Retrievers with Constrained Resources","created":"2024-07-30","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":"2305.05486","title":"MAUPQA: Massive Automatically-created Polish Question Answering Dataset","created":"2023-05-09","cited_by_count":11,"area":null},{"id":"2310.08232","title":"Language Models are Universal Embedders","created":"2023-10-12","cited_by_count":11,"area":null},{"id":"2305.09025","title":"Soft Prompt Decoding for Multilingual Dense Retrieval","created":"2023-05-15","cited_by_count":10,"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":"2411.01192","title":"Swan and ArabicMTEB: Dialect-Aware, Arabic-Centric, Cross-Lingual, and Cross-Cultural Embedding Models and Benchmarks","created":"2024-11-02","cited_by_count":10,"area":null},{"id":"2502.11571","title":"FaMTEB: Massive Text Embedding Benchmark in Persian Language","created":"2025-02-17","cited_by_count":10,"area":null},{"id":"2301.12847","title":"Finding the Law: Enhancing Statutory Article Retrieval via Graph Neural Networks","created":"2023-01-30","cited_by_count":9,"area":null},{"id":"2408.10151","title":"Multilingual Needle in a Haystack: Investigating Long-Context Behavior of Multilingual Large Language Models","created":"2024-08-19","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":"2406.10806","title":"ptt5-v2: A Closer Look at Continued Pretraining of T5 Models for the Portuguese Language","created":"2024-06-16","cited_by_count":8,"area":null},{"id":"2412.12806","title":"Cross-Dialect Information Retrieval: Information Access in Low-Resource and High-Variance Languages","created":"2024-12-17","cited_by_count":8,"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":"2404.04487","title":"KazQAD: Kazakh Open-Domain Question Answering Dataset","created":"2024-04-06","cited_by_count":7,"area":null},{"id":"2501.19264","title":"mFollowIR: a Multilingual Benchmark for Instruction Following in Retrieval","created":"2025-01-31","cited_by_count":7,"area":null},{"id":"2411.12235","title":"BoolQuestions: Does Dense Retrieval Understand Boolean Logic in Language?","created":"2024-11-19","cited_by_count":6,"area":null},{"id":"2412.08329","title":"BEIR-NL: Zero-shot Information Retrieval Benchmark for the Dutch Language","created":"2024-12-11","cited_by_count":6,"area":null},{"id":"2607.27178","title":"DenseOn with the LateOn: Fully Open Dense and Late-Interaction Models for Multilingual, Long-Context, and Code Search","created":"2026-07-29","cited_by_count":6,"area":null},{"id":"2309.08469","title":"Silver Retriever: Advancing Neural Passage Retrieval for Polish Question Answering","created":"2023-09-15","cited_by_count":5,"area":null},{"id":"2311.01870","title":"Multi-EuP: The Multilingual European Parliament Dataset for Analysis of Bias in Information Retrieval","created":"2023-11-03","cited_by_count":5,"area":null},{"id":"2312.09508","title":"IndicIRSuite: Multilingual Dataset and Neural Information Models for Indian Languages","created":"2023-12-15","cited_by_count":5,"area":null},{"id":"2509.12340","title":"MTEB-NL and E5-NL: Embedding Benchmark and Models for Dutch","created":"2025-09-15","cited_by_count":5,"area":null},{"id":"2510.06888","title":"M3Retrieve: Benchmarking Multimodal Retrieval for Medicine","created":"2025-10-08","cited_by_count":5,"area":null},{"id":"2212.10448","title":"Parameter-efficient Zero-shot Transfer for Cross-Language Dense Retrieval with Adapters","created":"2022-12-20","cited_by_count":4,"area":null},{"id":"2304.01019","title":"Simple Yet Effective Neural Ranking and Reranking Baselines for Cross-Lingual Information Retrieval","created":"2023-04-03","cited_by_count":4,"area":null},{"id":"2305.05295","title":"Boosting Zero-shot Cross-lingual Retrieval by Training on Artificially Code-Switched Data","created":"2023-05-09","cited_by_count":4,"area":null},{"id":"2312.10171","title":"Pipeline and Dataset Generation for Automated Fact-checking in Almost Any Language","created":"2023-12-15","cited_by_count":4,"area":null},{"id":"2407.19527","title":"Open Sentence Embeddings for Portuguese with the Serafim PT* encoders family","created":"2024-07-28","cited_by_count":4,"area":null},{"id":"2501.10175","title":"Multi-stage Training of Bilingual Islamic LLM for Neural Passage Retrieval","created":"2025-01-17","cited_by_count":4,"area":null},{"id":"2502.11308","title":"ALGEN: Few-shot Inversion Attacks on Textual Embeddings using Alignment and Generation","created":"2025-02-16","cited_by_count":4,"area":null},{"id":"2505.00649","title":"Investigating Task Arithmetic for Zero-Shot Information Retrieval","created":"2025-05-01","cited_by_count":4,"area":null},{"id":"2510.07812","title":"Multilingual Generative Retrieval via Cross-lingual Semantic Compression","created":"2025-10-09","cited_by_count":4,"area":null},{"id":"2209.13738","title":"mRobust04: A Multilingual Version of the TREC Robust 2004 Benchmark","created":"2022-09-27","cited_by_count":3,"area":null},{"id":"2301.10444","title":"An Experimental Study on Pretraining Transformers from Scratch for IR","created":"2023-01-25","cited_by_count":3,"area":null},{"id":"2312.16144","title":"Towards Better Monolingual Japanese Retrievers with Multi-Vector Models","created":"2023-12-26","cited_by_count":3,"area":null},{"id":"2408.09437","title":"Hindi-BEIR : A Large Scale Retrieval Benchmark in Hindi","created":"2024-08-18","cited_by_count":3,"area":null},{"id":"2409.05994","title":"MessIRve: A Large-Scale Spanish Information Retrieval Dataset","created":"2024-09-09","cited_by_count":3,"area":null},{"id":"2411.06151","title":"Building an Efficient Multilingual Non-Profit IR System for the Islamic Domain Leveraging Multiprocessing Design in Rust","created":"2024-11-09","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":"2502.08638","title":"Examining Multilingual Embedding Models Cross-Lingually Through LLM-Generated Adversarial Examples","created":"2025-02-12","cited_by_count":3,"area":null},{"id":"2505.14156","title":"Unify Graph Learning with Text: Unleashing LLM Potentials for Session Search","created":"2025-05-20","cited_by_count":3,"area":null},{"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":"2509.06195","title":"Language Bias in Information Retrieval: The Nature of the Beast and Mitigation Methods","created":"2025-09-07","cited_by_count":3,"area":null},{"id":"2408.10536","title":"Synergistic Approach for Simultaneous Optimization of Monolingual, Cross-lingual, and Multilingual Information Retrieval","created":"2024-08-20","cited_by_count":2,"area":null},{"id":"2409.05401","title":"Benchmarking and Building Zero-Shot Hindi Retrieval Model with Hindi-BEIR and NLLB-E5","created":"2024-09-09","cited_by_count":2,"area":null},{"id":"2409.07737","title":"Ruri: Japanese General Text Embeddings","created":"2024-09-12","cited_by_count":2,"area":null},{"id":"2503.08379","title":"JurisTCU: A Brazilian Portuguese Information Retrieval Dataset with Query Relevance Judgments","created":"2025-03-11","cited_by_count":2,"area":null},{"id":"2504.12879","title":"Building Russian Benchmark for Evaluation of Information Retrieval Models","created":"2025-04-17","cited_by_count":2,"area":null},{"id":"2506.01615","title":"IndicRAGSuite: Large-Scale Datasets and a Benchmark for Indian Language RAG Systems","created":"2025-06-02","cited_by_count":2,"area":"rag"},{"id":"2506.08592","title":"Dense Retrievers Can Fail on Simple Queries: Revealing The Granularity Dilemma of Embeddings","created":"2025-06-10","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":"2601.04768","title":"LANGSAE EDITING: Improving Multilingual Information Retrieval via Post-hoc Language Identity Removal","created":"2026-01-08","cited_by_count":2,"area":null},{"id":"2210.14837","title":"NeuralSearchX: Serving a Multi-billion-parameter Reranker for Multilingual Metasearch at a Low Cost","created":"2022-10-26","cited_by_count":1,"area":null},{"id":"2404.16248","title":"URL: Universal Referential Knowledge Linking via Task-instructed Representation Compression","created":"2024-04-24","cited_by_count":1,"area":null},{"id":"2409.01357","title":"Know When to Fuse: Investigating Non-English Hybrid Retrieval in the Legal Domain","created":"2024-09-02","cited_by_count":1,"area":null},{"id":"2505.16008","title":"LAGO: Few-shot Crosslingual Embedding Inversion Attacks via Language Similarity-Aware Graph Optimization","created":"2025-05-21","cited_by_count":1,"area":null},{"id":"2509.15380","title":"Efficient and Versatile Model for Multilingual Information Retrieval of Islamic Text: Development and Deployment in Real-World Scenarios","created":"2025-09-18","cited_by_count":1,"area":null},{"id":"2606.01995","title":"CARTE: A Benchmark for Mapping Language Model Knowledge Across France","created":"2026-06-01","cited_by_count":1,"area":"lr"},{"id":"2606.18801","title":"SHIFT: Semantic Harmonization via Index-side Feature Transformation for Multilingual Information Retrieval","created":"2026-06-17","cited_by_count":1,"area":null},{"id":"2608.02189","title":"Disentangled Contrastive Learning for Zero-Shot Multilingual Dense Retrieval","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2111.05988","title":"Cross-language Information Retrieval","created":"2021-11-10","cited_by_count":0,"area":null},{"id":"2401.03590","title":"Building Efficient and Effective OpenQA Systems for Low-Resource Languages","created":"2024-01-07","cited_by_count":0,"area":null},{"id":"2402.02932","title":"Domain Adaptation of Multilingual Semantic Search -- Literature Review","created":"2024-02-05","cited_by_count":0,"area":null},{"id":"2406.10172","title":"Datasets for Multilingual Answer Sentence Selection","created":"2024-06-14","cited_by_count":0,"area":null},{"id":"2410.04620","title":"Passage Retrieval of Polish Texts Using OKAPI BM25 and an Ensemble of Cross Encoders","created":"2024-10-06","cited_by_count":0,"area":null},{"id":"2412.12997","title":"Enabling Low-Resource Language Retrieval: Establishing Baselines for Urdu MS MARCO","created":"2024-12-17","cited_by_count":0,"area":null},{"id":"2505.02154","title":"Interpreting Multilingual and Document-Length Sensitive Relevance Computations in Neural Retrieval Models through Axiomatic Causal Interventions","created":"2025-05-04","cited_by_count":0,"area":"mechinterp"},{"id":"2506.21913","title":"HyReC: Exploring Hybrid-based Retriever for Chinese","created":"2025-06-27","cited_by_count":0,"area":null},{"id":"2601.03496","title":"STELLA: Self-Reflective Terminology-Aware Framework for Building an Aerospace Information Retrieval Benchmark","created":"2026-01-07","cited_by_count":0,"area":null},{"id":"2601.10205","title":"One Instruction Does Not Fit All: How Well Do Embeddings Align Personas and Instructions in Low-Resource Indian Languages?","created":"2026-01-15","cited_by_count":0,"area":null},{"id":"2601.21759","title":"Influence Guided Sampling for Domain Adaptation of Text Retrievers","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2604.13721","title":"FRAGATA: Semantic Retrieval of HPC Support Tickets via Hybrid RAG over 20 Years of Request Tracker History","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2604.14448","title":"MARCA: A Checklist-Based Benchmark for Multilingual Web Search","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2604.21511","title":"From Tokens to Concepts: Leveraging SAE for SPLADE","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2604.23396","title":"Lost in Decoding? Reproducing and Stress-Testing the Look-Ahead Prior in Generative Retrieval","created":"2026-04-25","cited_by_count":0,"area":null}],"next_cursor":"100"}