{"list":"other","total":59,"rows":[{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"2002.08909","title":"REALM: Retrieval-Augmented Language Model Pre-Training","created":"2020-02-10","cited_by_count":2141},{"id":"2403.07974","title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","created":"2024-03-12","cited_by_count":2004},{"id":"2408.00118","title":"Gemma 2: Improving Open Language Models at a Practical Size","created":"2024-07-31","cited_by_count":1998},{"id":"1611.09268","title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","created":"2016-11-28","cited_by_count":1605},{"id":"2112.04426","title":"Improving language models by retrieving from trillions of tokens","created":"2021-12-08","cited_by_count":1293},{"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":"2007.01282","title":"Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering","created":"2020-07-02","cited_by_count":1210},{"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},{"id":"1911.00172","title":"Generalization through Memorization: Nearest Neighbor Language Models","created":"2019-11-01","cited_by_count":800},{"id":"2102.04664","title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","created":"2021-02-09","cited_by_count":744},{"id":"2308.03281","title":"Towards General Text Embeddings with Multi-stage Contrastive Learning","created":"2023-08-07","cited_by_count":723},{"id":"2302.00083","title":"In-Context Retrieval-Augmented Language Models","created":"2023-01-31","cited_by_count":702},{"id":"1909.09436","title":"CodeSearchNet Challenge: Evaluating the State of Semantic Code Search","created":"2019-09-20","cited_by_count":654},{"id":"2305.14627","title":"Enabling Large Language Models to Generate Text with Citations","created":"2023-05-24","cited_by_count":595},{"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":"2211.08411","title":"Large Language Models Struggle to Learn Long-Tail Knowledge","created":"2022-11-15","cited_by_count":458},{"id":"2303.12570","title":"RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation","created":"2023-03-22","cited_by_count":367},{"id":"2305.07922","title":"CodeT5+: Open Code Large Language Models for Code Understanding and Generation","created":"2023-05-13","cited_by_count":333},{"id":"2310.03214","title":"FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation","created":"2023-10-05","cited_by_count":318},{"id":"2401.00396","title":"RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models","created":"2023-12-31","cited_by_count":283},{"id":"2406.19314","title":"LiveBench: A Challenging, Contamination-Limited LLM Benchmark","created":"2024-06-27","cited_by_count":262},{"id":"2207.13332","title":"RealTime QA: What's the Answer Right Now?","created":"2022-07-27","cited_by_count":244},{"id":"2409.12941","title":"Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation","created":"2024-09-19","cited_by_count":162},{"id":"2407.12883","title":"BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval","created":"2024-07-16","cited_by_count":158},{"id":"2402.14207","title":"Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models","created":"2024-02-22","cited_by_count":154},{"id":"2409.10173","title":"jina-embeddings-v3: Multilingual Embeddings With Task LoRA","created":"2024-09-16","cited_by_count":141},{"id":"2309.10621","title":"Large language models can accurately predict searcher preferences","created":"2023-09-19","cited_by_count":131},{"id":"2010.11856","title":"XOR QA: Cross-lingual Open-Retrieval Question Answering","created":"2020-10-22","cited_by_count":121},{"id":"2412.19048","title":"Jasper and Stella: distillation of SOTA embedding models","created":"2024-12-26","cited_by_count":112},{"id":"2310.19923","title":"Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documents","created":"2023-10-30","cited_by_count":104},{"id":"2406.14497","title":"CodeRAG-Bench: Can Retrieval Augment Code Generation?","created":"2024-06-20","cited_by_count":91},{"id":"2304.09161","title":"Perspectives on Large Language Models for Relevance Judgment","created":"2023-04-13","cited_by_count":85},{"id":"2407.02883","title":"CoIR: A Comprehensive Benchmark for Code Information Retrieval Models","created":"2024-07-03","cited_by_count":60},{"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":"2412.01007","title":"CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Reranking","created":"2024-12-01","cited_by_count":37},{"id":"2404.06347","title":"RAR-b: Reasoning as Retrieval Benchmark","created":"2024-04-09","cited_by_count":36},{"id":"2406.16828","title":"Ragnar\\\"ok: A Reusable RAG Framework and Baselines for TREC 2024 Retrieval-Augmented Generation Track","created":"2024-06-24","cited_by_count":32},{"id":"2407.15353","title":"Customized Retrieval Augmented Generation and Benchmarking for EDA Tool Documentation QA","created":"2024-07-22","cited_by_count":28},{"id":"2411.09607","title":"Initial Nugget Evaluation Results for the TREC 2024 RAG Track with the AutoNuggetizer Framework","created":"2024-11-14","cited_by_count":28},{"id":"2402.15089","title":"AttributionBench: How Hard is Automatic Attribution Evaluation?","created":"2024-02-23","cited_by_count":26},{"id":"2404.02103","title":"CLAPNQ: Cohesive Long-form Answers from Passages in Natural Questions for RAG systems","created":"2024-04-02","cited_by_count":25},{"id":"2104.09399","title":"TREC Deep Learning Track: Reusable Test Collections in the Large Data Regime","created":"2021-04-19","cited_by_count":23},{"id":"2402.17896","title":"Researchy Questions: A Dataset of Multi-Perspective, Decompositional Questions for LLM Web Agents","created":"2024-02-27","cited_by_count":23},{"id":"2405.00982","title":"On the Evaluation of Machine-Generated Reports","created":"2024-05-02","cited_by_count":23},{"id":"2411.08275","title":"A Large-Scale Study of Relevance Assessments with Large Language Models: An Initial Look","created":"2024-11-13","cited_by_count":18},{"id":"2405.12363","title":"Question-Based Retrieval using Atomic Units for Enterprise RAG","created":"2024-05-20","cited_by_count":17},{"id":"1908.09804","title":"Neural Code Search Evaluation Dataset","created":"2019-08-26","cited_by_count":13},{"id":"2503.15231","title":"When LLMs Meet API Documentation: Can Retrieval Augmentation Aid Code Generation Just as It Helps Developers?","created":"2025-03-19","cited_by_count":13},{"id":"2212.14464","title":"Result Diversification in Search and Recommendation: A Survey","created":"2022-12-29","cited_by_count":12},{"id":"2404.04044","title":"A Comparison of Methods for Evaluating Generative IR","created":"2024-04-05","cited_by_count":11},{"id":"2405.13177","title":"A Workbench for Autograding Retrieve/Generate Systems","created":"2024-05-21","cited_by_count":9},{"id":"2404.00657","title":"Observations on Building RAG Systems for Technical Documents","created":"2024-03-31","cited_by_count":8},{"id":"2411.11767","title":"Drowning in Documents: Consequences of Scaling Reranker Inference","created":"2024-11-18","cited_by_count":8}],"next_cursor":null}