{"list":"other","total":102,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2004.04906","title":"Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-04-10","cited_by_count":3824},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"1606.09282","title":"Learning without Forgetting","created":"2016-06-29","cited_by_count":2496},{"id":"2408.03314","title":"Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters","created":"2024-08-06","cited_by_count":1986},{"id":"2503.09516","title":"Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning","created":"2025-03-12","cited_by_count":1444},{"id":"2501.19393","title":"s1: Simple test-time scaling","created":"2025-01-31","cited_by_count":1341},{"id":"2104.08663","title":"BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models","created":"2021-04-17","cited_by_count":1252},{"id":"2004.12832","title":"ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT","created":"2020-04-27","cited_by_count":1178},{"id":"2212.10509","title":"Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions","created":"2022-12-20","cited_by_count":923},{"id":"2007.00808","title":"Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval","created":"2020-07-01","cited_by_count":849},{"id":"2302.00093","title":"Large Language Models Can Be Easily Distracted by Irrelevant Context","created":"2023-01-31","cited_by_count":841},{"id":"1901.04085","title":"Passage Re-ranking with BERT","created":"2019-01-13","cited_by_count":645},{"id":"2210.07316","title":"MTEB: Massive Text Embedding Benchmark","created":"2022-10-13","cited_by_count":640},{"id":"2010.04592","title":"Contrastive Learning with Hard Negative Samples","created":"2020-10-09","cited_by_count":628},{"id":"2111.07783","title":"FILIP: Fine-grained Interactive Language-Image Pre-Training","created":"2021-11-09","cited_by_count":627},{"id":"2212.10403","title":"Towards Reasoning in Large Language Models: A Survey","created":"2022-12-20","cited_by_count":596},{"id":"2401.18059","title":"RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval","created":"2024-01-31","cited_by_count":532},{"id":"2105.03011","title":"A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers","created":"2021-05-07","cited_by_count":486},{"id":"2112.01488","title":"ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction","created":"2021-12-02","cited_by_count":476},{"id":"2405.17428","title":"NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models","created":"2024-05-27","cited_by_count":472},{"id":"1412.6622","title":"Deep metric learning using Triplet network","created":"2014-12-20","cited_by_count":422},{"id":"2010.08191","title":"RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-10-16","cited_by_count":413},{"id":"1803.06643","title":"The Web as a Knowledge-base for Answering Complex Questions","created":"2018-03-18","cited_by_count":410},{"id":"2004.10645","title":"AmbigQA: Answering Ambiguous Open-domain Questions","created":"2020-04-22","cited_by_count":390},{"id":"2401.08281","title":"The Faiss library","created":"2024-01-16","cited_by_count":376},{"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},{"id":"2212.09741","title":"One Embedder, Any Task: Instruction-Finetuned Text Embeddings","created":"2022-12-19","cited_by_count":333},{"id":"2308.07107","title":"Large Language Models for Information Retrieval: A Survey","created":"2023-08-14","cited_by_count":331},{"id":"2401.00368","title":"Improving Text Embeddings with Large Language Models","created":"2023-12-31","cited_by_count":303},{"id":"2106.15110","title":"Time-Aware Language Models as Temporal Knowledge Bases","created":"2021-06-29","cited_by_count":296},{"id":"2107.05720","title":"SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking","created":"2021-07-12","cited_by_count":286},{"id":"2205.13147","title":"Matryoshka Representation Learning","created":"2022-05-26","cited_by_count":282},{"id":"2311.11944","title":"FinanceBench: A New Benchmark for Financial Question Answering","created":"2023-11-20","cited_by_count":270},{"id":"2102.01951","title":"Mind the Gap: Assessing Temporal Generalization in Neural Language Models","created":"2021-02-03","cited_by_count":230},{"id":"2005.00181","title":"Sparse, Dense, and Attentional Representations for Text Retrieval","created":"2020-05-01","cited_by_count":214},{"id":"2112.08608","title":"QuALITY: Question Answering with Long Input Texts, Yes!","created":"2021-12-16","cited_by_count":208},{"id":"2311.09210","title":"Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Models","created":"2023-11-15","cited_by_count":184},{"id":"1601.01280","title":"Language to Logical Form with Neural Attention","created":"2016-01-06","cited_by_count":158},{"id":"2407.12883","title":"BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval","created":"2024-07-16","cited_by_count":158},{"id":"2312.02724","title":"RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze!","created":"2023-12-05","cited_by_count":155},{"id":"2404.00610","title":"RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation","created":"2024-03-31","cited_by_count":147},{"id":"2109.08535","title":"Simple Entity-Centric Questions Challenge Dense Retrievers","created":"2021-09-17","cited_by_count":140},{"id":"2303.08559","title":"Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples!","created":"2023-03-15","cited_by_count":119},{"id":"2002.09758","title":"Unsupervised Question Decomposition for Question Answering","created":"2020-02-22","cited_by_count":118},{"id":"2104.07186","title":"COIL: Revisit Exact Lexical Match in Information Retrieval with Contextualized Inverted List","created":"2021-04-15","cited_by_count":113},{"id":"2508.21038","title":"On the Theoretical Limitations of Embedding-Based Retrieval","created":"2025-08-28","cited_by_count":104},{"id":"2205.09707","title":"PLAID: An Efficient Engine for Late Interaction Retrieval","created":"2022-05-19","cited_by_count":101},{"id":"2312.06648","title":"Dense X Retrieval: What Retrieval Granularity Should We Use?","created":"2023-12-11","cited_by_count":88},{"id":"2310.14122","title":"Beyond Yes and No: Improving Zero-Shot LLM Rankers via Scoring Fine-Grained Relevance Labels","created":"2023-10-21","cited_by_count":86},{"id":"2403.20327","title":"Gecko: Versatile Text Embeddings Distilled from Large Language Models","created":"2024-03-29","cited_by_count":83},{"id":"2412.13678","title":"Clio: Privacy-Preserving Insights into Real-World AI Use","created":"2024-12-18","cited_by_count":72},{"id":"2502.18418","title":"Rank1: Test-Time Compute for Reranking in Information Retrieval","created":"2025-02-25","cited_by_count":70},{"id":"2110.06918","title":"Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?","created":"2021-10-13","cited_by_count":60},{"id":"2205.00656","title":"Debiased Contrastive Learning of Unsupervised Sentence Representations","created":"2022-05-02","cited_by_count":56},{"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},{"id":"2403.12958","title":"Dated Data: Tracing Knowledge Cutoffs in Large Language Models","created":"2024-03-19","cited_by_count":51},{"id":"2106.03719","title":"Incremental False Negative Detection for Contrastive Learning","created":"2021-06-07","cited_by_count":48},{"id":"2402.05131","title":"Financial Report Chunking for Effective Retrieval Augmented Generation","created":"2024-02-05","cited_by_count":46},{"id":"2006.16742","title":"FairRec: Fairness-aware News Recommendation with Decomposed Adversarial Learning","created":"2020-06-30","cited_by_count":44},{"id":"2410.13070","title":"Is Semantic Chunking Worth the Computational Cost?","created":"2024-10-16","cited_by_count":43},{"id":"2106.09373","title":"Unsupervised Path Representation Learning with Curriculum Negative Sampling","created":"2021-06-17","cited_by_count":42},{"id":"2402.03367","title":"RAG-Fusion: a New Take on Retrieval-Augmented Generation","created":"2024-01-31","cited_by_count":42},{"id":"2203.08372","title":"Multi-View Document Representation Learning for Open-Domain Dense Retrieval","created":"2022-03-16","cited_by_count":41},{"id":"2406.12433","title":"LLM4Rerank: LLM-based Auto-Reranking Framework for Recommendations","created":"2024-06-18","cited_by_count":40},{"id":"2302.07920","title":"InfoNCE Loss Provably Learns Cluster-Preserving Representations","created":"2023-02-15","cited_by_count":37},{"id":"2508.07995","title":"DIVER: A Multi-Stage Approach for Reasoning-intensive Information Retrieval","created":"2025-08-11","cited_by_count":37},{"id":"1908.09756","title":"Differentiable Product Quantization for End-to-End Embedding Compression","created":"2019-08-26","cited_by_count":36},{"id":"2410.02338","title":"How Much Can RAG Help the Reasoning of LLM?","created":"2024-10-03","cited_by_count":31},{"id":"2109.03438","title":"ArchivalQA: A Large-scale Benchmark Dataset for Open Domain Question Answering over Historical News Collections","created":"2021-09-08","cited_by_count":30},{"id":"2206.00212","title":"Negative Sampling for Contrastive Representation Learning: A Review","created":"2022-06-01","cited_by_count":23},{"id":"2202.02093","title":"Temporal Attention for Language Models","created":"2022-02-04","cited_by_count":21},{"id":"2303.09331","title":"Model Based Explanations of Concept Drift","created":"2023-03-16","cited_by_count":21},{"id":"2406.12824","title":"From RAGs to rich parameters: Probing how language models utilize external knowledge over parametric information for factual queries","created":"2024-06-18","cited_by_count":16},{"id":"2402.17238","title":"Does Negative Sampling Matter? A Review with Insights into its Theory and Applications","created":"2024-02-27","cited_by_count":15},{"id":"2502.21024","title":"TempRetriever: Fusion-based Temporal Dense Passage Retrieval for Time-Sensitive Questions","created":"2025-02-28","cited_by_count":15},{"id":"2509.11552","title":"HiChunk: Evaluating and Enhancing Retrieval-Augmented Generation with Hierarchical Chunking","created":"2025-09-15","cited_by_count":12},{"id":"2510.06999","title":"Towards Reliable Retrieval in RAG Systems for Large Legal Datasets","created":"2025-10-08","cited_by_count":12},{"id":"2207.07874","title":"Model-Aware Contrastive Learning: Towards Escaping the Dilemmas","created":"2022-07-16","cited_by_count":11},{"id":"2405.14211","title":"ChronosLex: Time-aware Incremental Training for Temporal Generalization of Legal Classification Tasks","created":"2024-05-23","cited_by_count":11},{"id":"2404.18655","title":"Revealing the Parametric Knowledge of Language Models: A Unified Framework for Attribution Methods","created":"2024-04-29","cited_by_count":9},{"id":"2501.05485","title":"S2 Chunking: A Hybrid Framework for Document Segmentation Through Integrated Spatial and Semantic Analysis","created":"2025-01-08","cited_by_count":8},{"id":"2103.06523","title":"Improving Bi-encoder Document Ranking Models with Two Rankers and Multi-teacher Distillation","created":"2021-03-11","cited_by_count":7},{"id":"2411.19463","title":"Understanding the Fundamental Design Decisions of Retrieval-Augmented Generation Systems","created":"2024-11-29","cited_by_count":7},{"id":"2502.04645","title":"Pathway to Relevance: How Cross-Encoders Implement a Semantic Variant of BM25","created":"2025-02-07","cited_by_count":6},{"id":"2506.10859","title":"Precise Zero-Shot Pointwise Ranking with LLMs through Post-Aggregated Global Context Information","created":"2025-06-12","cited_by_count":6},{"id":"2506.16035","title":"Vision-Guided Chunking Is All You Need: Enhancing RAG with Multimodal Document Understanding","created":"2025-06-19","cited_by_count":6},{"id":"2308.08378","title":"Advancing continual lifelong learning in neural information retrieval: definition, dataset, framework, and empirical evaluation","created":"2023-08-16","cited_by_count":5},{"id":"2404.00590","title":"CuSINeS: Curriculum-driven Structure Induced Negative Sampling for Statutory Article Retrieval","created":"2024-03-31","cited_by_count":5},{"id":"2506.00037","title":"Query Drift Compensation: Enabling Compatibility in Continual Learning of Retrieval Embedding Models","created":"2025-05-27","cited_by_count":5},{"id":"2507.06782","title":"Temporal Information Retrieval via Time-Specifier Model Merging","created":"2025-07-09","cited_by_count":5},{"id":"2511.02770","title":"Beyond Single Embeddings: Capturing Diverse Targets with Multi-Query Retrieval","created":"2025-11-04","cited_by_count":5},{"id":"2507.22337","title":"A Comprehensive Taxonomy of Negation for NLP and Neural Retrievers","created":"2025-07-30","cited_by_count":4},{"id":"2509.06544","title":"Reason to Retrieve: Enhancing Query Understanding through Decomposition and Interpretation","created":"2025-09-08","cited_by_count":4},{"id":"2510.13217","title":"LLM-guided Hierarchical Search for End-to-end Reasoning Intensive Retrieval","created":"2025-10-15","cited_by_count":4},{"id":"2506.19897","title":"Can LLMs Replace Humans During Code Chunking?","created":"2025-06-24","cited_by_count":2}],"next_cursor":"100"}