{"total":41,"rows":[{"id":"2112.01488","title":"ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction","created":"2021-12-02","cited_by_count":476,"area":null},{"id":"2204.10628","title":"Autoregressive Search Engines: Generating Substrings as Document Identifiers","created":"2022-04-22","cited_by_count":113,"area":null},{"id":"2211.09260","title":"Task-aware Retrieval with Instructions","created":"2022-11-16","cited_by_count":107,"area":null},{"id":"2106.14807","title":"A Few Brief Notes on DeepImpact, COIL, and a Conceptual Framework for Information Retrieval Techniques","created":"2021-06-28","cited_by_count":69,"area":null},{"id":"2112.09924","title":"The Web Is Your Oyster - Knowledge-Intensive NLP against a Very Large Web Corpus","created":"2021-12-18","cited_by_count":60,"area":null},{"id":"2110.07803","title":"Attacking Open-domain Question Answering by Injecting Misinformation","created":"2021-10-15","cited_by_count":41,"area":null},{"id":"2212.01349","title":"Nonparametric Masked Language Modeling","created":"2022-12-02","cited_by_count":40,"area":null},{"id":"2110.02369","title":"EntQA: Entity Linking as Question Answering","created":"2021-10-05","cited_by_count":34,"area":null},{"id":"2203.03367","title":"Multi-CPR: A Multi Domain Chinese Dataset for Passage Retrieval","created":"2022-03-07","cited_by_count":27,"area":null},{"id":"2110.01529","title":"A Proposed Conceptual Framework for a Representational Approach to Information Retrieval","created":"2021-10-04","cited_by_count":24,"area":null},{"id":"2402.14526","title":"Balanced Data Sampling for Language Model Training with Clustering","created":"2024-02-22","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":"2211.07886","title":"A Survey for Efficient Open Domain Question Answering","created":"2022-11-15","cited_by_count":20,"area":null},{"id":"2110.06612","title":"Exploring Dense Retrieval for Dialogue Response Selection","created":"2021-10-13","cited_by_count":11,"area":null},{"id":"2407.12982","title":"Retrieval-Enhanced Machine Learning: Synthesis and Opportunities","created":"2024-07-17","cited_by_count":11,"area":null},{"id":"2112.07771","title":"Boosted Dense Retriever","created":"2021-12-14","cited_by_count":10,"area":null},{"id":"2211.12707","title":"Can Open-Domain QA Reader Utilize External Knowledge Efficiently like Humans?","created":"2022-11-23","cited_by_count":10,"area":null},{"id":"2110.01599","title":"Encoder Adaptation of Dense Passage Retrieval for Open-Domain Question Answering","created":"2021-10-04","cited_by_count":8,"area":null},{"id":"2201.05409","title":"Progressively Optimized Bi-Granular Document Representation for Scalable Embedding Based Retrieval","created":"2022-01-14","cited_by_count":7,"area":null},{"id":"2203.03235","title":"Pre-trained Token-replaced Detection Model as Few-shot Learner","created":"2022-03-07","cited_by_count":7,"area":null},{"id":"2210.01371","title":"A Study on the Efficiency and Generalization of Light Hybrid Retrievers","created":"2022-10-04","cited_by_count":7,"area":null},{"id":"2112.09628","title":"Sparsifying Sparse Representations for Passage Retrieval by Top-$k$ Masking","created":"2021-12-17","cited_by_count":5,"area":null},{"id":"2210.07093","title":"Query Expansion Using Contextual Clue Sampling with Language Models","created":"2022-10-13","cited_by_count":5,"area":null},{"id":"2303.15311","title":"Improving Dual-Encoder Training through Dynamic Indexes for Negative Mining","created":"2023-03-27","cited_by_count":5,"area":null},{"id":"2304.03401","title":"Noise-Robust Dense Retrieval via Contrastive Alignment Post Training","created":"2023-04-06","cited_by_count":5,"area":null},{"id":"2107.14740","title":"Automatic Claim Review for Climate Science via Explanation Generation","created":"2021-07-30","cited_by_count":4,"area":null},{"id":"2205.09393","title":"Two-Step Question Retrieval for Open-Domain QA","created":"2022-05-19","cited_by_count":4,"area":null},{"id":"2205.11498","title":"Injecting Domain Adaptation with Learning-to-hash for Effective and Efficient Zero-shot Dense Retrieval","created":"2022-05-23","cited_by_count":4,"area":null},{"id":"2407.12529","title":"Crafting the Path: Robust Query Rewriting for Information Retrieval","created":"2024-07-17","cited_by_count":4,"area":null},{"id":"2506.16444","title":"REIS: A High-Performance and Energy-Efficient Retrieval System with In-Storage Processing","created":"2025-06-19","cited_by_count":4,"area":null},{"id":"2606.11780","title":"What Limits Does Quantization Place on Dense Top-$k$ Retrieval? A Theoretical Study","created":"2026-06-10","cited_by_count":4,"area":null},{"id":"2204.02906","title":"Knowledge Base Index Compression via Dimensionality and Precision Reduction","created":"2022-04-06","cited_by_count":2,"area":null},{"id":"2302.11953","title":"MFBE: Leveraging Multi-Field Information of FAQs for Efficient Dense Retrieval","created":"2023-02-23","cited_by_count":1,"area":null},{"id":"2605.18271","title":"From Volume to Value: Preference-Aligned Memory Construction for On-Device RAG","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2111.09927","title":"Quality and Cost Trade-offs in Passage Re-ranking Task","created":"2021-11-18","cited_by_count":0,"area":null},{"id":"2206.08046","title":"An Open-Domain QA System for e-Governance","created":"2022-06-16","cited_by_count":0,"area":null},{"id":"2210.10584","title":"Enhanced vectors for top-k document retrieval in Question Answering","created":"2022-10-08","cited_by_count":0,"area":null},{"id":"2309.10339","title":"KoBigBird-large: Transformation of Transformer for Korean Language Understanding","created":"2023-09-19","cited_by_count":0,"area":null},{"id":"2405.01924","title":"Semi-Parametric Retrieval via Binary Bag-of-Tokens Index","created":"2024-05-03","cited_by_count":0,"area":null},{"id":"2511.12300","title":"Do LLMs and Humans Find the Same Questions Difficult? A Case Study on Japanese Quiz Answering","created":"2025-11-15","cited_by_count":0,"area":null},{"id":"2609.16391","title":"Where Post-Training Quantization Breaks Text Embedders: A Measured Map Across Four Embedder Families","created":"2026-09-14","cited_by_count":0,"area":null}],"next_cursor":null}