{"total":101,"rows":[{"id":"2212.14024","title":"Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP","created":"2022-12-28","cited_by_count":318,"area":"rag"},{"id":"2407.01449","title":"ColPali: Efficient Document Retrieval with Vision Language Models","created":"2024-06-27","cited_by_count":195,"area":"mllm"},{"id":"2302.07452","title":"How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrieval","created":"2023-02-15","cited_by_count":118,"area":null},{"id":"2305.14292","title":"WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipedia","created":"2023-05-23","cited_by_count":67,"area":null},{"id":"2309.17133","title":"Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question Answering","created":"2023-09-29","cited_by_count":51,"area":"rag"},{"id":"2212.02027","title":"Retrieval as Attention: End-to-end Learning of Retrieval and Reading within a Single Transformer","created":"2022-12-05","cited_by_count":45,"area":null},{"id":"2402.08327","title":"PreFLMR: Scaling Up Fine-Grained Late-Interaction Multi-modal Retrievers","created":"2024-02-13","cited_by_count":42,"area":"mllm"},{"id":"2509.18095","title":"MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible Late Interaction","created":"2025-09-22","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":"2304.01982","title":"Rethinking the Role of Token Retrieval in Multi-Vector Retrieval","created":"2023-04-04","cited_by_count":31,"area":null},{"id":"2305.07614","title":"NevIR: Negation in Neural Information Retrieval","created":"2023-05-12","cited_by_count":29,"area":null},{"id":"2207.03834","title":"An Efficiency Study for SPLADE Models","created":"2022-07-08","cited_by_count":26,"area":null},{"id":"2404.02935","title":"KnowHalu: Hallucination Detection via Multi-Form Knowledge Based Factual Checking","created":"2024-04-03","cited_by_count":26,"area":"lr"},{"id":"2409.14683","title":"Reducing the Footprint of Multi-Vector Retrieval with Minimal Performance Impact via Token Pooling","created":"2024-09-23","cited_by_count":25,"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":"2509.23883","title":"DocPruner: A Storage-Efficient Framework for Multi-Vector Visual Document Retrieval via Adaptive Patch-Level Embedding Pruning","created":"2025-09-28","cited_by_count":20,"area":null},{"id":"2211.10411","title":"CITADEL: Conditional Token Interaction via Dynamic Lexical Routing for Efficient and Effective Multi-Vector Retrieval","created":"2022-11-18","cited_by_count":19,"area":null},{"id":"2209.01335","title":"Neural Approaches to Multilingual Information Retrieval","created":"2022-09-03","cited_by_count":18,"area":null},{"id":"2508.03555","title":"PyLate: Flexible Training and Retrieval for Late Interaction Models","created":"2025-08-05","cited_by_count":18,"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":"2503.01980","title":"Recurrence-Enhanced Vision-and-Language Transformers for Robust Multimodal Document Retrieval","created":"2025-03-03","cited_by_count":13,"area":"mllm"},{"id":"2504.01818","title":"Efficient Constant-Space Multi-Vector Retrieval","created":"2025-04-02","cited_by_count":12,"area":null},{"id":"2510.05038","title":"Guided Query Refinement: Multimodal Hybrid Retrieval with Test-Time Optimization","created":"2025-10-06","cited_by_count":12,"area":null},{"id":"2602.19549","title":"Sculpting the Vector Space: Towards Efficient Multi-Vector Visual Document Retrieval via Prune-then-Merge Framework","created":"2026-02-23","cited_by_count":10,"area":null},{"id":"2602.21202","title":"Multi-Vector Index Compression in Any Modality","created":"2026-02-24","cited_by_count":10,"area":null},{"id":"2312.05417","title":"ESPN: Memory-Efficient Multi-Vector Information Retrieval","created":"2023-12-09","cited_by_count":8,"area":null},{"id":"2404.14989","title":"A Reproducibility Study of PLAID","created":"2024-04-23","cited_by_count":8,"area":null},{"id":"2605.06235","title":"OBLIQ-Bench: Exposing Overlooked Bottlenecks in Modern Retrievers with Latent and Implicit Queries","created":"2026-05-07","cited_by_count":8,"area":null},{"id":"2505.17810","title":"VIBE: Vector Index Benchmark for Embeddings","created":"2025-05-23","cited_by_count":6,"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":"2505.19189","title":"POQD: Performance-Oriented Query Decomposer for Multi-vector retrieval","created":"2025-05-25","cited_by_count":5,"area":"rag"},{"id":"2212.01340","title":"Moving Beyond Downstream Task Accuracy for Information Retrieval Benchmarking","created":"2022-12-02","cited_by_count":4,"area":null},{"id":"2301.09715","title":"PrimeQA: The Prime Repository for State-of-the-Art Multilingual Question Answering Research and Development","created":"2023-01-23","cited_by_count":4,"area":null},{"id":"2508.01405","title":"Balancing the Blend: An Experimental Analysis of Trade-offs in Hybrid Search","created":"2025-08-02","cited_by_count":4,"area":"rag"},{"id":"2510.22215","title":"Hybrid-Vector Retrieval for Visually Rich Documents: Combining Single-Vector Efficiency and Multi-Vector Accuracy","created":"2025-10-25","cited_by_count":4,"area":null},{"id":"2601.20131","title":"Taxonomy of the Retrieval System Framework: Pitfalls and Paradigms","created":"2026-01-27","cited_by_count":4,"area":null},{"id":"2405.00975","title":"PLAID SHIRTTT for Large-Scale Streaming Dense Retrieval","created":"2024-05-02","cited_by_count":3,"area":null},{"id":"2410.01383","title":"PairDistill: Pairwise Relevance Distillation for Dense Retrieval","created":"2024-10-02","cited_by_count":3,"area":null},{"id":"2411.04129","title":"AmazonQAC: A Large-Scale, Naturalistic Query Autocomplete Dataset","created":"2024-10-22","cited_by_count":3,"area":null},{"id":"2411.08334","title":"MIRe: Enhancing Multimodal Queries Representation via Fusion-Free Modality Interaction for Multimodal Retrieval","created":"2024-11-13","cited_by_count":3,"area":null},{"id":"2504.04065","title":"Enabling Collaborative Parametric Knowledge Calibration for Retrieval-Augmented Vision Question Answering","created":"2025-04-05","cited_by_count":2,"area":"rag"},{"id":"2504.12778","title":"Towards Lossless Token Pruning in Late-Interaction Retrieval Models","created":"2025-04-17","cited_by_count":2,"area":"inference"},{"id":"2504.16264","title":"CLIRudit: Cross-Lingual Information Retrieval of Scientific Documents","created":"2025-04-22","cited_by_count":2,"area":null},{"id":"2510.12327","title":"Simple Projection Variants Improve ColBERT Performance","created":"2025-10-14","cited_by_count":2,"area":null},{"id":"2511.22843","title":"Breaking the Visual Shortcuts in Multimodal Knowledge-Based Visual Question Answering","created":"2025-11-28","cited_by_count":2,"area":null},{"id":"2602.17687","title":"IRPAPERS: A Visual Document Benchmark for Scientific Retrieval and Question Answering","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2605.02489","title":"GRAIL: A Deep-Granularity Hybrid Resonance Framework for Real-Time Agent Discovery via SLM-Enhanced Indexing","created":"2026-05-04","cited_by_count":2,"area":"agents"},{"id":"2606.07654","title":"MM-Matryoshka: Towards Budget-Elastic Visual Document Retrieval via a 2D Multimodal Matryoshka Training Framework","created":"2026-06-03","cited_by_count":2,"area":"mllm"},{"id":"2607.04605","title":"Do All Visual Tokens Matter Equally? Object-Evidence Preserving Token Merging for Vision-Language Retrieval","created":"2026-07-06","cited_by_count":2,"area":"inference"},{"id":"2404.08118","title":"HLTCOE at TREC 2023 NeuCLIR Track","created":"2024-04-11","cited_by_count":1,"area":null},{"id":"2404.08134","title":"Extending Translate-Train for ColBERT-X to African Language CLIR","created":"2024-04-11","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":"2410.11655","title":"Retrieval Augmented Spelling Correction for E-Commerce Applications","created":"2024-10-15","cited_by_count":1,"area":"rag"},{"id":"2511.00444","title":"LIR: The First Workshop on Late Interaction and Multi Vector Retrieval @ ECIR 2026","created":"2025-11-01","cited_by_count":1,"area":null},{"id":"2511.16528","title":"TurkColBERT: A Benchmark of Dense and Late-Interaction Models for Turkish Information Retrieval","created":"2025-11-20","cited_by_count":1,"area":null},{"id":"2512.22416","title":"Hallucination Detection and Evaluation of Large Language Model","created":"2025-12-27","cited_by_count":1,"area":null},{"id":"2601.21853","title":"LEMUR: Learned Multi-Vector Retrieval","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2603.20336","title":"GEM: A Native Graph-based Index for Multi-Vector Retrieval","created":"2026-03-20","cited_by_count":1,"area":null},{"id":"2604.05087","title":"Document Optimization for Black-Box Retrieval via Reinforcement Learning","created":"2026-04-06","cited_by_count":1,"area":null},{"id":"2604.09982","title":"Reproduction Beyond Benchmarks: ConstBERT and ColBERT-v2 Across Backends and Query Distributions","created":"2026-04-11","cited_by_count":1,"area":null},{"id":"2604.28142","title":"Efficient Multivector Retrieval with Token-Aware Clustering and Hierarchical Indexing","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2605.07210","title":"DiffRetriever: Parallel Representative Tokens for Retrieval with Diffusion Language Models","created":"2026-05-08","cited_by_count":1,"area":"diffusion"},{"id":"2605.30120","title":"No More K-means: Single-Stage Sparse Coding for Efficient Multi-Vector Retrieval","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2606.26439","title":"TileMaxSim: IO-Aware GPU MaxSim Scoring with Dimension Tiling and Fused Product Quantization","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2608.21529","title":"DamageScope: Vision-Language Retrieval at Scale for Disaster Damage Assessment from Satellite Imagery","created":"2026-08-21","cited_by_count":1,"area":"mllm"},{"id":"2609.07561","title":"EigenLI: Spectral Approximations to Late Interaction","created":"2026-09-07","cited_by_count":1,"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":"2405.15028","title":"AGRaME: Any-Granularity Ranking with Multi-Vector Embeddings","created":"2024-05-23","cited_by_count":0,"area":null},{"id":"2411.12921","title":"A Comparative Study of Text Retrieval Models on DaReCzech","created":"2024-11-19","cited_by_count":0,"area":null},{"id":"2504.10250","title":"MURR: Model Updating with Regularized Replay for Searching a Document Stream","created":"2025-04-14","cited_by_count":0,"area":null},{"id":"2508.08514","title":"DeCAL Tokenwise Compression","created":"2025-08-11","cited_by_count":0,"area":null},{"id":"2510.08976","title":"MIRAGE: Runtime Scheduling for Multi-Vector Image Retrieval with Hierarchical Decomposition","created":"2025-10-10","cited_by_count":0,"area":"mllm"},{"id":"2510.22479","title":"Contextual Tokenization for Graph Inverted Indices","created":"2025-10-26","cited_by_count":0,"area":null},{"id":"2512.12458","title":"Breaking the Curse of Dimensionality: On the Stability of Modern Vector Retrieval","created":"2025-12-13","cited_by_count":0,"area":"rag"},{"id":"2602.10444","title":"Chamfer-Linkage for Hierarchical Agglomerative Clustering","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2604.05253","title":"Spike Hijacking in Late-Interaction Retrieval","created":"2026-04-06","cited_by_count":0,"area":null},{"id":"2604.06245","title":"CraterBench-R: Instance-Level Crater Retrieval for Planetary Scale","created":"2026-04-06","cited_by_count":0,"area":null},{"id":"2604.16576","title":"On the Robustness of LLM-Based Dense Retrievers: A Systematic Analysis of Generalizability and Stability","created":"2026-04-17","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":"2605.24914","title":"MVR-cache: Optimizing Semantic Caching via Multi-Vector Retrieval and Learned Prompt Segmentation","created":"2026-05-24","cited_by_count":0,"area":null},{"id":"2605.29158","title":"PROTOCOL: Late Interaction Retrieval for Protein Homolog Search","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.05568","title":"ColBERTSaR: Sparsified ColBERT Index via Product Quantization","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2606.19960","title":"Stellar: Scalable Multimodal Document Retrieval for Natural Language Queries","created":"2026-06-18","cited_by_count":0,"area":"rag"},{"id":"2607.18626","title":"PLAID-PRF: Pseudo-Relevance Feedback with Centroid-like Tokens in PLAID","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2608.10636","title":"DistilVDR: A Compact End-to-End Visual Document Retriever via Dual-Student Distillation","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.14648","title":"Stop Indexing at Full Precision: Revisiting Clustering for Vector Embeddings","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.26344","title":"MoganColBERT-TR: A Late-Interaction Multi-Vector Retrieval Model for Turkish","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2608.29951","title":"Spatial Matryoshka Training for Multi-Granularity Visual Document Retrieval","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.01657","title":"NeoMME: A Single-Tower Multimodal-Native Multilingual Foundation Encoder for Efficient Fine-Tuning and Inference","created":"2026-08-31","cited_by_count":0,"area":"mllm"},{"id":"2609.02486","title":"ViSAR: Training-Free Adaptive-$k$ Retrieval for Visual Document Question Answering","created":"2026-09-02","cited_by_count":0,"area":"mllm"},{"id":"2609.07262","title":"Query-Aware Token Budgeting for Efficient Late-Interaction Visual Document Retrieval","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.22562","title":"AdaMerge: Tuning-Free Patch Compression for Multi-Vector Visual Document Retrieval","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.23646","title":"Beyond Relevance: Structured Semantic Supervision for Product Search with LLM-Augmented Annotations","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2609.25859","title":"BELXTR: Biomedical Entity Linking via Contextualized Token Retrieval","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.36074","title":"GEM-KMeans: Memory-Efficient and Accurate Clustering on Massive Scale with GPU Optimization","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.38473","title":"Re-ranking and Late Interaction Drive Retrieval Quality: A Controlled Comparison of RAG Strategies for Scientific Question Answering","created":"2026-09-29","cited_by_count":0,"area":"rag"},{"id":"2610.05099","title":"Small Agents with Semantic Search: Efficient Multilingual Code Localization","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.09920","title":"Inverting Multi-Vector Visual Document Indices","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.13277","title":"Beyond the Final Embedding: Retrieving Memories from Token-Level Evidence","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.14196","title":"Simple Linear Corrections for Compression in Late Interaction","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":"100"}