{"list":"other","total":63,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"2004.04906","title":"Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-04-10","cited_by_count":3824},{"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":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"2002.08909","title":"REALM: Retrieval-Augmented Language Model Pre-Training","created":"2020-02-10","cited_by_count":2141},{"id":"2307.13854","title":"WebArena: A Realistic Web Environment for Building Autonomous Agents","created":"2023-07-25","cited_by_count":2006},{"id":"2308.14508","title":"LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding","created":"2023-08-28","cited_by_count":1417},{"id":"2406.12045","title":"$\\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains","created":"2024-06-17","cited_by_count":1402},{"id":"2404.06654","title":"RULER: What's the Real Context Size of Your Long-Context Language Models?","created":"2024-04-09","cited_by_count":1346},{"id":"2112.04426","title":"Improving language models by retrieving from trillions of tokens","created":"2021-12-08","cited_by_count":1293},{"id":"2011.01060","title":"Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps","created":"2020-11-02","cited_by_count":1282},{"id":"2010.03768","title":"ALFWorld: Aligning Text and Embodied Environments for Interactive Learning","created":"2020-10-08","cited_by_count":1205},{"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":"2108.00573","title":"MuSiQue: Multihop Questions via Single-hop Question Composition","created":"2021-08-02","cited_by_count":916},{"id":"1903.00161","title":"DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs","created":"2019-03-01","cited_by_count":903},{"id":"2301.12652","title":"REPLUG: Retrieval-Augmented Black-Box Language Models","created":"2023-01-30","cited_by_count":792},{"id":"2210.07316","title":"MTEB: Massive Text Embedding Benchmark","created":"2022-10-13","cited_by_count":640},{"id":"2009.02252","title":"KILT: a Benchmark for Knowledge Intensive Language Tasks","created":"2020-09-04","cited_by_count":573},{"id":"2410.05229","title":"GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models","created":"2024-10-07","cited_by_count":550},{"id":"1803.06643","title":"The Web as a Knowledge-base for Answering Complex Questions","created":"2018-03-18","cited_by_count":410},{"id":"2402.13718","title":"$\\infty$Bench: Extending Long Context Evaluation Beyond 100K Tokens","created":"2024-02-21","cited_by_count":367},{"id":"2102.01017","title":"Measuring and Improving Consistency in Pretrained Language Models","created":"2021-02-01","cited_by_count":364},{"id":"2012.13048","title":"ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Language","created":"2020-12-24","cited_by_count":324},{"id":"2310.03214","title":"FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation","created":"2023-10-05","cited_by_count":318},{"id":"1502.05698","title":"Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks","created":"2015-02-19","cited_by_count":314},{"id":"2306.13304","title":"ToolQA: A Dataset for LLM Question Answering with External Tools","created":"2023-06-23","cited_by_count":274},{"id":"2311.09476","title":"ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systems","created":"2023-11-16","cited_by_count":265},{"id":"2004.07347","title":"HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Data","created":"2020-04-15","cited_by_count":264},{"id":"2401.15391","title":"MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries","created":"2024-01-27","cited_by_count":257},{"id":"2207.13332","title":"RealTime QA: What's the Answer Right Now?","created":"2022-07-27","cited_by_count":244},{"id":"2307.12976","title":"Evaluating the Ripple Effects of Knowledge Editing in Language Models","created":"2023-07-24","cited_by_count":242},{"id":"2307.11088","title":"L-Eval: Instituting Standardized Evaluation for Long Context Language Models","created":"2023-07-20","cited_by_count":233},{"id":"2010.15875","title":"Retrieve, Program, Repeat: Complex Knowledge Base Question Answering via Alternate Meta-learning","created":"2020-10-29","cited_by_count":216},{"id":"2311.04939","title":"LooGLE: Can Long-Context Language Models Understand Long Contexts?","created":"2023-11-08","cited_by_count":202},{"id":"1710.06481","title":"Constructing Datasets for Multi-hop Reading Comprehension Across Documents","created":"2017-10-17","cited_by_count":190},{"id":"2405.13576","title":"FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Research","created":"2024-05-22","cited_by_count":166},{"id":"1908.06177","title":"CLUTRR: A Diagnostic Benchmark for Inductive Reasoning from Text","created":"2019-08-16","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":"2406.17419","title":"Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA","created":"2024-06-25","cited_by_count":122},{"id":"1909.04849","title":"A Discrete Hard EM Approach for Weakly Supervised Question Answering","created":"2019-09-11","cited_by_count":78},{"id":"2310.07064","title":"Large Language Models can Learn Rules","created":"2023-10-10","cited_by_count":69},{"id":"2210.12714","title":"Generative Knowledge Graph Construction: A Review","created":"2022-10-23","cited_by_count":49},{"id":"1808.07980","title":"Ontology Reasoning with Deep Neural Networks","created":"2018-08-24","cited_by_count":40},{"id":"1906.06606","title":"Multi-Hop Paragraph Retrieval for Open-Domain Question Answering","created":"2019-06-15","cited_by_count":34},{"id":"2407.01102","title":"BERGEN: A Benchmarking Library for Retrieval-Augmented Generation","created":"2024-07-01","cited_by_count":31},{"id":"2406.11811","title":"RepLiQA: A Question-Answering Dataset for Benchmarking LLMs on Unseen Reference Content","created":"2024-06-17","cited_by_count":26},{"id":"2403.09040","title":"RAGGED: Towards Informed Design of Scalable and Stable RAG Systems","created":"2024-03-14","cited_by_count":24},{"id":"2409.04617","title":"Sparse Rewards Can Self-Train Dialogue Agents","created":"2024-09-06","cited_by_count":6},{"id":"2412.15529","title":"XRAG: eXamining the Core -- Benchmarking Foundational Components in Advanced Retrieval-Augmented Generation","created":"2024-12-20","cited_by_count":3}],"next_cursor":null}