{"list":"other","total":69,"rows":[{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2004.04906","title":"Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-04-10","cited_by_count":3824},{"id":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212},{"id":"2305.14325","title":"Improving Factuality and Reasoning in Language Models through Multiagent Debate","created":"2023-05-23","cited_by_count":1784},{"id":"1611.09268","title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","created":"2016-11-28","cited_by_count":1605},{"id":"2002.10957","title":"MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers","created":"2020-02-25","cited_by_count":1463},{"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":"2112.09118","title":"Unsupervised Dense Information Retrieval with Contrastive Learning","created":"2021-12-16","cited_by_count":1216},{"id":"1909.10351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","created":"2019-09-23","cited_by_count":1167},{"id":"2305.19118","title":"Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate","created":"2023-05-30","cited_by_count":1011},{"id":"2007.00808","title":"Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval","created":"2020-07-01","cited_by_count":849},{"id":"2308.07201","title":"ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate","created":"2023-08-14","cited_by_count":742},{"id":"2212.10496","title":"Precise Zero-Shot Dense Retrieval without Relevance Labels","created":"2022-12-20","cited_by_count":517},{"id":"2112.01488","title":"ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction","created":"2021-12-02","cited_by_count":476},{"id":"2309.15217","title":"Ragas: Automated Evaluation of Retrieval Augmented Generation","created":"2023-09-26","cited_by_count":418},{"id":"2003.06713","title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","created":"2020-03-14","cited_by_count":376},{"id":"2109.05052","title":"Entity-Based Knowledge Conflicts in Question Answering","created":"2021-09-10","cited_by_count":356},{"id":"2309.13007","title":"ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs","created":"2023-09-22","cited_by_count":309},{"id":"2003.07820","title":"Overview of the TREC 2019 deep learning track","created":"2020-03-17","cited_by_count":286},{"id":"2402.06782","title":"Debating with More Persuasive LLMs Leads to More Truthful Answers","created":"2024-02-09","cited_by_count":266},{"id":"2401.15391","title":"MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries","created":"2024-01-27","cited_by_count":257},{"id":"2409.12941","title":"Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation","created":"2024-09-19","cited_by_count":162},{"id":"2303.07678","title":"Query2doc: Query Expansion with Large Language Models","created":"2023-03-14","cited_by_count":149},{"id":"2210.13701","title":"Rich Knowledge Sources Bring Complex Knowledge Conflicts: Recalibrating Models to Reflect Conflicting Evidence","created":"2022-10-25","cited_by_count":144},{"id":"2309.10621","title":"Large language models can accurately predict searcher preferences","created":"2023-09-19","cited_by_count":131},{"id":"2407.11005","title":"RAGBench: Explainable Benchmark for Retrieval-Augmented Generation Systems","created":"2024-06-25","cited_by_count":117},{"id":"2205.04733","title":"From Distillation to Hard Negative Sampling: Making Sparse Neural IR Models More Effective","created":"2022-05-10","cited_by_count":98},{"id":"2305.11595","title":"Examining Inter-Consistency of Large Language Models Collaboration: An In-depth Analysis via Debate","created":"2023-05-19","cited_by_count":97},{"id":"2406.04744","title":"CRAG -- Comprehensive RAG Benchmark","created":"2024-06-07","cited_by_count":97},{"id":"2401.07324","title":"Small LLMs Are Weak Tool Learners: A Multi-LLM Agent","created":"2024-01-14","cited_by_count":93},{"id":"2304.09161","title":"Perspectives on Large Language Models for Relevance Judgment","created":"2023-04-13","cited_by_count":85},{"id":"2303.11315","title":"Context-faithful Prompting for Large Language Models","created":"2023-03-20","cited_by_count":80},{"id":"2203.00211","title":"Investigating Selective Prediction Approaches Across Several Tasks in IID, OOD, and Adversarial Settings","created":"2022-03-01","cited_by_count":66},{"id":"2504.13079","title":"Retrieval-Augmented Generation with Conflicting Evidence","created":"2025-04-17","cited_by_count":63},{"id":"2405.05374","title":"Arctic-Embed: Scalable, Efficient, and Accurate Text Embedding Models","created":"2024-05-08","cited_by_count":61},{"id":"2412.04506","title":"Arctic-Embed 2.0: Multilingual Retrieval Without Compromise","created":"2024-12-03","cited_by_count":58},{"id":"2106.00882","title":"Efficient Passage Retrieval with Hashing for Open-domain Question Answering","created":"2021-06-02","cited_by_count":53},{"id":"2410.02584","title":"Towards Implicit Bias Detection and Mitigation in Multi-Agent LLM Interactions","created":"2024-10-03","cited_by_count":51},{"id":"2402.18050","title":"MEGAnno+: A Human-LLM Collaborative Annotation System","created":"2024-02-28","cited_by_count":47},{"id":"2008.09093","title":"PARADE: Passage Representation Aggregation for Document Reranking","created":"2020-08-20","cited_by_count":44},{"id":"2406.06519","title":"UMBRELA: UMbrela is the (Open-Source Reproduction of the) Bing RELevance Assessor","created":"2024-06-10","cited_by_count":42},{"id":"2402.15610","title":"Selective \"Selective Prediction\": Reducing Unnecessary Abstention in Vision-Language Reasoning","created":"2024-02-23","cited_by_count":40},{"id":"2502.11028","title":"Mind the Confidence Gap: Overconfidence, Calibration, and Distractor Effects in Large Language Models","created":"2025-02-16","cited_by_count":40},{"id":"2405.16282","title":"Confidence Under the Hood: An Investigation into the Confidence-Probability Alignment in Large Language Models","created":"2024-05-25","cited_by_count":34},{"id":"2302.11266","title":"One-Shot Labeling for Automatic Relevance Estimation","created":"2023-02-22","cited_by_count":31},{"id":"2505.02151","title":"Large Language Models are overconfident and amplify human bias","created":"2025-05-04","cited_by_count":30},{"id":"2412.17156","title":"LLM-based relevance assessment still can't replace human relevance assessment","created":"2024-12-22","cited_by_count":27},{"id":"2409.15133","title":"Don't Use LLMs to Make Relevance Judgments","created":"2024-09-23","cited_by_count":26},{"id":"2508.06225","title":"Overconfidence in LLM-as-a-Judge: Diagnosis and Confidence-Driven Solution","created":"2025-08-08","cited_by_count":18},{"id":"2401.06311","title":"Exploring the Best Practices of Query Expansion with Large Language Models","created":"2024-01-12","cited_by_count":17},{"id":"2208.00511","title":"Aggretriever: A Simple Approach to Aggregate Textual Representations for Robust Dense Passage Retrieval","created":"2022-07-31","cited_by_count":12},{"id":"2311.09175","title":"Can Query Expansion Improve Generalization of Strong Cross-Encoder Rankers?","created":"2023-11-15","cited_by_count":12},{"id":"2411.06877","title":"LLM-Assisted Relevance Assessments: When Should We Ask LLMs for Help?","created":"2024-11-11","cited_by_count":11},{"id":"2504.17137","title":"MIRAGE: A Metric-Intensive Benchmark for Retrieval-Augmented Generation Evaluation","created":"2025-04-23","cited_by_count":11},{"id":"2409.13884","title":"A Multi-LLM Debiasing Framework","created":"2024-09-20","cited_by_count":10},{"id":"2411.02454","title":"Graph-based Confidence Calibration for Large Language Models","created":"2024-11-03","cited_by_count":10},{"id":"2502.08514","title":"Faithful, Unfaithful or Ambiguous? Multi-Agent Debate with Initial Stance for Summary Evaluation","created":"2025-02-12","cited_by_count":10},{"id":"2408.16312","title":"SynDL: A Large-Scale Synthetic Test Collection for Passage Retrieval","created":"2024-08-29","cited_by_count":9},{"id":"2508.07827","title":"Evaluating Large Language Models as Expert Annotators","created":"2025-08-11","cited_by_count":9},{"id":"2502.13417","title":"RLTHF: Targeted Human Feedback for LLM Alignment","created":"2025-02-19","cited_by_count":8},{"id":"2507.05981","title":"Multi-Agent Debate Strategies to Enhance Requirements Engineering with Large Language Models","created":"2025-07-08","cited_by_count":8},{"id":"2404.08695","title":"Enhancing Question Answering for Enterprise Knowledge Bases using Large Language Models","created":"2024-04-10","cited_by_count":7},{"id":"2205.03284","title":"Dimension Reduction for Efficient Dense Retrieval via Conditional Autoencoder","created":"2022-05-06","cited_by_count":6},{"id":"2303.16857","title":"Did You Mean...? Confidence-based Trade-offs in Semantic Parsing","created":"2023-03-29","cited_by_count":5},{"id":"2406.08891","title":"Robust Information Retrieval","created":"2024-06-13","cited_by_count":5},{"id":"2406.16048","title":"Evaluating D-MERIT of Partial-annotation on Information Retrieval","created":"2024-06-23","cited_by_count":4},{"id":"2507.18343","title":"Hybrid Annotation for Propaganda Detection: Integrating LLM Pre-Annotations with Human Intelligence","created":"2025-07-24","cited_by_count":4},{"id":"2406.07299","title":"Exploring Large Language Models for Relevance Judgments in Tetun","created":"2024-06-11","cited_by_count":3},{"id":"2406.14162","title":"DIRAS: Efficient LLM Annotation of Document Relevance in Retrieval Augmented Generation","created":"2024-06-20","cited_by_count":3}],"next_cursor":null}