{"list":"other","total":73,"rows":[{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"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":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"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":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"2404.16130","title":"From Local to Global: A Graph RAG Approach to Query-Focused Summarization","created":"2024-04-24","cited_by_count":1453},{"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":"2112.09118","title":"Unsupervised Dense Information Retrieval with Contrastive Learning","created":"2021-12-16","cited_by_count":1216},{"id":"2210.03350","title":"Measuring and Narrowing the Compositionality Gap in Language Models","created":"2022-10-07","cited_by_count":1075},{"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":"2306.08302","title":"Unifying Large Language Models and Knowledge Graphs: A Roadmap","created":"2023-06-14","cited_by_count":668},{"id":"2104.08164","title":"Editing Factual Knowledge in Language Models","created":"2021-04-16","cited_by_count":553},{"id":"2401.18059","title":"RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval","created":"2024-01-31","cited_by_count":532},{"id":"2304.14767","title":"Dissecting Recall of Factual Associations in Auto-Regressive Language Models","created":"2023-04-28","cited_by_count":528},{"id":"2110.11309","title":"Fast Model Editing at Scale","created":"2021-10-21","cited_by_count":498},{"id":"2112.01488","title":"ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction","created":"2021-12-02","cited_by_count":476},{"id":"2112.07899","title":"Large Dual Encoders Are Generalizable Retrievers","created":"2021-12-15","cited_by_count":456},{"id":"1906.05317","title":"COMET: Commonsense Transformers for Automatic Knowledge Graph Construction","created":"2019-06-12","cited_by_count":450},{"id":"2206.06520","title":"Memory-Based Model Editing at Scale","created":"2022-06-13","cited_by_count":447},{"id":"2402.13718","title":"$\\infty$Bench: Extending Long Context Evaluation Beyond 100K Tokens","created":"2024-02-21","cited_by_count":367},{"id":"2305.15294","title":"Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy","created":"2023-05-24","cited_by_count":346},{"id":"2305.09645","title":"StructGPT: A General Framework for Large Language Model to Reason over Structured Data","created":"2023-05-16","cited_by_count":343},{"id":"2305.13300","title":"Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts","created":"2023-05-22","cited_by_count":341},{"id":"2310.01061","title":"Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning","created":"2023-10-02","cited_by_count":328},{"id":"2310.02207","title":"Language Models Represent Space and Time","created":"2023-10-03","cited_by_count":316},{"id":"2402.13753","title":"LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens","created":"2024-02-21","cited_by_count":313},{"id":"2209.02299","title":"A Survey of Machine Unlearning","created":"2022-09-06","cited_by_count":312},{"id":"2305.14795","title":"MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions","created":"2023-05-24","cited_by_count":300},{"id":"2209.10063","title":"Generate rather than Retrieve: Large Language Models are Strong Context Generators","created":"2022-09-21","cited_by_count":298},{"id":"2110.07178","title":"Symbolic Knowledge Distillation: from General Language Models to Commonsense Models","created":"2021-10-14","cited_by_count":270},{"id":"2309.12307","title":"LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models","created":"2023-09-21","cited_by_count":244},{"id":"2402.10171","title":"Data Engineering for Scaling Language Models to 128K Context","created":"2024-02-15","cited_by_count":186},{"id":"2401.01286","title":"A Comprehensive Study of Knowledge Editing for Large Language Models","created":"2024-01-02","cited_by_count":163},{"id":"2009.12756","title":"Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval","created":"2020-09-27","cited_by_count":162},{"id":"2204.06031","title":"A Review on Language Models as Knowledge Bases","created":"2022-04-12","cited_by_count":157},{"id":"2210.09338","title":"Deep Bidirectional Language-Knowledge Graph Pretraining","created":"2022-10-17","cited_by_count":156},{"id":"1911.10470","title":"Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering","created":"2019-11-24","cited_by_count":147},{"id":"2310.05029","title":"Walking Down the Memory Maze: Beyond Context Limit through Interactive Reading","created":"2023-10-08","cited_by_count":133},{"id":"2402.04624","title":"MEMORYLLM: Towards Self-Updatable Large Language Models","created":"2024-02-07","cited_by_count":93},{"id":"2312.06648","title":"Dense X Retrieval: What Retrieval Granularity Should We Use?","created":"2023-12-11","cited_by_count":88},{"id":"2304.13007","title":"Answering Questions by Meta-Reasoning over Multiple Chains of Thought","created":"2023-04-25","cited_by_count":87},{"id":"1911.03631","title":"Hierarchical Graph Network for Multi-hop Question Answering","created":"2019-11-09","cited_by_count":83},{"id":"2403.04121","title":"Can Large Language Models Reason and Plan?","created":"2024-03-07","cited_by_count":82},{"id":"2306.06427","title":"Boosting Language Models Reasoning with Chain-of-Knowledge Prompting","created":"2023-06-10","cited_by_count":77},{"id":"2308.09729","title":"MindMap: Knowledge Graph Prompting Sparks Graph of Thoughts in Large Language Models","created":"2023-08-17","cited_by_count":73},{"id":"1905.05460","title":"Cognitive Graph for Multi-Hop Reading Comprehension at Scale","created":"2019-05-14","cited_by_count":65},{"id":"1905.06933","title":"Dynamically Fused Graph Network for Multi-hop Reasoning","created":"2019-05-16","cited_by_count":63},{"id":"2212.09736","title":"Don't Generate, Discriminate: A Proposal for Grounding Language Models to Real-World Environments","created":"2022-12-19","cited_by_count":57},{"id":"2308.13198","title":"Journey to the Center of the Knowledge Neurons: Discoveries of Language-Independent Knowledge Neurons and Degenerate Knowledge Neurons","created":"2023-08-25","cited_by_count":56},{"id":"1909.08041","title":"Revealing the Importance of Semantic Retrieval for Machine Reading at Scale","created":"2019-09-17","cited_by_count":50},{"id":"2305.11159","title":"Aligning Instruction Tasks Unlocks Large Language Models as Zero-Shot Relation Extractors","created":"2023-05-18","cited_by_count":45},{"id":"2305.12392","title":"PiVe: Prompting with Iterative Verification Improving Graph-based Generative Capability of LLMs","created":"2023-05-21","cited_by_count":44},{"id":"2405.08944","title":"Challenges in Deploying Long-Context Transformers: A Theoretical Peak Performance Analysis","created":"2024-05-14","cited_by_count":44},{"id":"2310.02129","title":"Unveiling the Pitfalls of Knowledge Editing for Large Language Models","created":"2023-10-03","cited_by_count":43},{"id":"2109.06747","title":"Adaptive Information Seeking for Open-Domain Question Answering","created":"2021-09-14","cited_by_count":29},{"id":"2205.11725","title":"A Survey on Neural Open Information Extraction: Current Status and Future Directions","created":"2022-05-24","cited_by_count":27},{"id":"2402.13449","title":"CAMELoT: Towards Large Language Models with Training-Free Consolidated Associative Memory","created":"2024-02-21","cited_by_count":24},{"id":"2311.03734","title":"Leveraging Structured Information for Explainable Multi-hop Question Answering and Reasoning","created":"2023-11-07","cited_by_count":22},{"id":"1909.07598","title":"Multi-step Entity-centric Information Retrieval for Multi-Hop Question Answering","created":"2019-09-17","cited_by_count":20},{"id":"2012.15534","title":"HopRetriever: Retrieve Hops over Wikipedia to Answer Complex Questions","created":"2020-12-31","cited_by_count":19},{"id":"2403.06932","title":"ERA-CoT: Improving Chain-of-Thought through Entity Relationship Analysis","created":"2024-03-11","cited_by_count":18},{"id":"2311.14740","title":"AutoKG: Efficient Automated Knowledge Graph Generation for Language Models","created":"2023-11-22","cited_by_count":17},{"id":"2109.01048","title":"Pre-training Language Model Incorporating Domain-specific Heterogeneous Knowledge into A Unified Representation","created":"2021-09-02","cited_by_count":11},{"id":"2311.09762","title":"Graph Elicitation for Guiding Multi-Step Reasoning in Large Language Models","created":"2023-11-16","cited_by_count":10},{"id":"2310.03052","title":"Memoria: Resolving Fateful Forgetting Problem through Human-Inspired Memory Architecture","created":"2023-10-04","cited_by_count":8},{"id":"2307.00335","title":"Single Sequence Prediction over Reasoning Graphs for Multi-hop QA","created":"2023-07-01","cited_by_count":5},{"id":"2211.08228","title":"When to Use What: An In-Depth Comparative Empirical Analysis of OpenIE Systems for Downstream Applications","created":"2022-11-15","cited_by_count":4}],"next_cursor":null}