{"list":"other","total":75,"rows":[{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"2308.08155","title":"AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation","created":"2023-08-16","cited_by_count":1988},{"id":"2308.14508","title":"LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding","created":"2023-08-28","cited_by_count":1417},{"id":"2205.10625","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","created":"2022-05-21","cited_by_count":1407},{"id":"2112.04426","title":"Improving language models by retrieving from trillions of tokens","created":"2021-12-08","cited_by_count":1293},{"id":"2108.12409","title":"Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation","created":"2021-08-27","cited_by_count":1103},{"id":"2308.09687","title":"Graph of Thoughts: Solving Elaborate Problems with Large Language Models","created":"2023-08-18","cited_by_count":886},{"id":"2503.13657","title":"Why Do Multi-Agent LLM Systems Fail?","created":"2025-03-17","cited_by_count":604},{"id":"1712.07040","title":"The NarrativeQA Reading Comprehension Challenge","created":"2017-12-19","cited_by_count":597},{"id":"2306.02561","title":"LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion","created":"2023-06-05","cited_by_count":564},{"id":"2305.04091","title":"Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models","created":"2023-05-06","cited_by_count":560},{"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":"2502.11089","title":"Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention","created":"2025-02-16","cited_by_count":407},{"id":"2402.13718","title":"$\\infty$Bench: Extending Long Context Evaluation Beyond 100K Tokens","created":"2024-02-21","cited_by_count":367},{"id":"2104.05938","title":"QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization","created":"2021-04-13","cited_by_count":365},{"id":"2104.02112","title":"Efficient Attentions for Long Document Summarization","created":"2021-04-05","cited_by_count":345},{"id":"2410.10819","title":"DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads","created":"2024-10-14","cited_by_count":288},{"id":"2412.04984","title":"Frontier Models are Capable of In-context Scheming","created":"2024-12-06","cited_by_count":287},{"id":"2404.02060","title":"Long-context LLMs Struggle with Long In-context Learning","created":"2024-04-02","cited_by_count":286},{"id":"2310.02124","title":"Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View","created":"2023-10-03","cited_by_count":222},{"id":"2402.10200","title":"Chain-of-Thought Reasoning Without Prompting","created":"2024-02-15","cited_by_count":210},{"id":"2311.04939","title":"LooGLE: Can Long-Context Language Models Understand Long Contexts?","created":"2023-11-08","cited_by_count":202},{"id":"2404.07143","title":"Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention","created":"2024-04-10","cited_by_count":200},{"id":"2310.10844","title":"Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks","created":"2023-10-16","cited_by_count":194},{"id":"2306.07174","title":"Augmenting Language Models with Long-Term Memory","created":"2023-06-12","cited_by_count":189},{"id":"2402.10171","title":"Data Engineering for Scaling Language Models to 128K Context","created":"2024-02-15","cited_by_count":186},{"id":"2310.05029","title":"Walking Down the Memory Maze: Beyond Context Limit through Interactive Reading","created":"2023-10-08","cited_by_count":133},{"id":"2212.10554","title":"A Length-Extrapolatable Transformer","created":"2022-12-20","cited_by_count":127},{"id":"2401.12954","title":"Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffolding","created":"2024-01-23","cited_by_count":117},{"id":"2503.17407","title":"A Comprehensive Survey on Long Context Language Modeling","created":"2025-03-20","cited_by_count":117},{"id":"2402.03620","title":"Self-Discover: Large Language Models Self-Compose Reasoning Structures","created":"2024-02-06","cited_by_count":110},{"id":"2307.15337","title":"Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation","created":"2023-07-28","cited_by_count":105},{"id":"2309.17234","title":"Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation","created":"2023-09-29","cited_by_count":96},{"id":"2212.04092","title":"Successive Prompting for Decomposing Complex Questions","created":"2022-12-08","cited_by_count":94},{"id":"2409.12640","title":"Michelangelo: Long Context Evaluations Beyond Haystacks via Latent Structure Queries","created":"2024-09-19","cited_by_count":88},{"id":"2404.17140","title":"Small Language Models Need Strong Verifiers to Self-Correct Reasoning","created":"2024-04-26","cited_by_count":86},{"id":"2312.01823","title":"Exchange-of-Thought: Enhancing Large Language Model Capabilities through Cross-Model Communication","created":"2023-12-04","cited_by_count":82},{"id":"2402.05136","title":"LV-Eval: A Balanced Long-Context Benchmark with 5 Length Levels Up to 256K","created":"2024-02-06","cited_by_count":81},{"id":"2310.17512","title":"CompeteAI: Understanding the Competition Dynamics in Large Language Model-based Agents","created":"2023-10-26","cited_by_count":65},{"id":"2311.08562","title":"MAgIC: Investigation of Large Language Model Powered Multi-Agent in Cognition, Adaptability, Rationality and Collaboration","created":"2023-11-14","cited_by_count":57},{"id":"2401.04658","title":"Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models","created":"2024-01-09","cited_by_count":57},{"id":"2406.13121","title":"Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More?","created":"2024-06-19","cited_by_count":56},{"id":"2405.18719","title":"Contextual Position Encoding: Learning to Count What's Important","created":"2024-05-29","cited_by_count":54},{"id":"2406.11612","title":"Long Code Arena: a Set of Benchmarks for Long-Context Code Models","created":"2024-06-17","cited_by_count":50},{"id":"2401.04536","title":"Evaluating Language Model Agency through Negotiations","created":"2024-01-09","cited_by_count":48},{"id":"2406.14909","title":"Mixture of Attention Spans: Optimizing LLM Inference Efficiency with Heterogeneous Sliding-Window Lengths","created":"2024-06-21","cited_by_count":44},{"id":"2406.14550","title":"GraphReader: Building Graph-based Agent to Enhance Long-Context Abilities of Large Language Models","created":"2024-06-20","cited_by_count":43},{"id":"2402.03367","title":"RAG-Fusion: a New Take on Retrieval-Augmented Generation","created":"2024-01-31","cited_by_count":42},{"id":"2402.16499","title":"LLMArena: Assessing Capabilities of Large Language Models in Dynamic Multi-Agent Environments","created":"2024-02-26","cited_by_count":36},{"id":"2311.09198","title":"Never Lost in the Middle: Mastering Long-Context Question Answering with Position-Agnostic Decompositional Training","created":"2023-11-15","cited_by_count":32},{"id":"2403.12766","title":"NovelQA: Benchmarking Question Answering on Documents Exceeding 200K Tokens","created":"2024-03-18","cited_by_count":32},{"id":"2406.00936","title":"A Survey of Useful LLM Evaluation","created":"2024-06-03","cited_by_count":29},{"id":"2402.17124","title":"Fact-and-Reflection (FaR) Improves Confidence Calibration of Large Language Models","created":"2024-02-27","cited_by_count":27},{"id":"2405.15145","title":"CulturePark: Boosting Cross-cultural Understanding in Large Language Models","created":"2024-05-24","cited_by_count":24},{"id":"2402.10689","title":"Cultural Commonsense Knowledge for Intercultural Dialogues","created":"2024-02-16","cited_by_count":20},{"id":"2410.15633","title":"GATEAU: Selecting Influential Samples for Long Context Alignment","created":"2024-10-21","cited_by_count":20},{"id":"2407.16695","title":"Stress-Testing Long-Context Language Models with Lifelong ICL and Task Haystack","created":"2024-07-23","cited_by_count":19},{"id":"2405.19846","title":"Quest: Query-centric Data Synthesis Approach for Long-context Scaling of Large Language Model","created":"2024-05-30","cited_by_count":16},{"id":"2407.18553","title":"REAPER: Reasoning based Retrieval Planning for Complex RAG Systems","created":"2024-07-26","cited_by_count":16},{"id":"2406.15019","title":"MedOdyssey: A Medical Domain Benchmark for Long Context Evaluation Up to 200K Tokens","created":"2024-06-21","cited_by_count":13},{"id":"2407.14112","title":"Large-Language-Model Enabled Semantic Communication Systems","created":"2024-07-19","cited_by_count":12},{"id":"2310.00576","title":"GrowLength: Accelerating LLMs Pretraining by Progressively Growing Training Length","created":"2023-10-01","cited_by_count":11},{"id":"2502.16860","title":"LongAttn: Selecting Long-context Training Data via Token-level Attention","created":"2025-02-24","cited_by_count":9},{"id":"2311.09101","title":"Towards A Unified View of Answer Calibration for Multi-Step Reasoning","created":"2023-11-15","cited_by_count":8},{"id":"2503.00392","title":"Progressive Sparse Attention: Algorithm and System Co-design for Efficient Attention in LLM Serving","created":"2025-03-01","cited_by_count":7},{"id":"2410.06328","title":"Auto-Evolve: Enhancing Large Language Model's Performance via Self-Reasoning Framework","created":"2024-10-08","cited_by_count":4},{"id":"2401.15050","title":"LongFin: A Multimodal Document Understanding Model for Long Financial Domain Documents","created":"2024-01-26","cited_by_count":3}],"next_cursor":null}