{"list":"other","total":68,"rows":[{"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":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1706.02216","title":"Inductive Representation Learning on Large Graphs","created":"2017-06-07","cited_by_count":6320},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"id":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"id":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823},{"id":"2310.02255","title":"MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts","created":"2023-10-03","cited_by_count":1614},{"id":"2306.00890","title":"LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day","created":"2023-06-01","cited_by_count":1305},{"id":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242},{"id":"2403.04132","title":"Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference","created":"2024-03-07","cited_by_count":1184},{"id":"2212.10511","title":"When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories","created":"2022-12-20","cited_by_count":1128},{"id":"2406.12793","title":"ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools","created":"2024-06-18","cited_by_count":1121},{"id":"1510.03055","title":"A Diversity-Promoting Objective Function for Neural Conversation Models","created":"2015-10-11","cited_by_count":1077},{"id":"2302.04023","title":"A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity","created":"2023-02-08","cited_by_count":894},{"id":"1801.07243","title":"Personalizing Dialogue Agents: I have a dog, do you have pets too?","created":"2018-01-22","cited_by_count":828},{"id":"2309.01219","title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","created":"2023-09-03","cited_by_count":698},{"id":"1710.03957","title":"DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset","created":"2017-10-11","cited_by_count":652},{"id":"2401.02954","title":"DeepSeek LLM: Scaling Open-Source Language Models with Longtermism","created":"2024-01-05","cited_by_count":642},{"id":"1811.06128","title":"Machine Learning for Combinatorial Optimization: a Methodological Tour d'Horizon","created":"2018-11-15","cited_by_count":623},{"id":"1704.01665","title":"Learning Combinatorial Optimization Algorithms over Graphs","created":"2017-04-05","cited_by_count":561},{"id":"2211.08411","title":"Large Language Models Struggle to Learn Long-Tail Knowledge","created":"2022-11-15","cited_by_count":458},{"id":"2406.11931","title":"DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence","created":"2024-06-17","cited_by_count":331},{"id":"2103.09430","title":"OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs","created":"2021-03-17","cited_by_count":329},{"id":"2305.15408","title":"Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspective","created":"2023-05-24","cited_by_count":294},{"id":"2309.17452","title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","created":"2023-09-29","cited_by_count":282},{"id":"2306.13304","title":"ToolQA: A Dataset for LLM Question Answering with External Tools","created":"2023-06-23","cited_by_count":274},{"id":"2307.03393","title":"Exploring the Potential of Large Language Models (LLMs) in Learning on Graphs","created":"2023-07-07","cited_by_count":274},{"id":"2305.10037","title":"Can Language Models Solve Graph Problems in Natural Language?","created":"2023-05-17","cited_by_count":252},{"id":"2301.12726","title":"Specializing Smaller Language Models towards Multi-Step Reasoning","created":"2023-01-30","cited_by_count":251},{"id":"2310.00149","title":"One for All: Towards Training One Graph Model for All Classification Tasks","created":"2023-09-29","cited_by_count":243},{"id":"2003.03600","title":"Reinforcement Learning for Combinatorial Optimization: A Survey","created":"2020-03-07","cited_by_count":236},{"id":"2405.14333","title":"DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data","created":"2024-05-23","cited_by_count":234},{"id":"2310.04560","title":"Talk like a Graph: Encoding Graphs for Large Language Models","created":"2023-10-06","cited_by_count":176},{"id":"2304.09797","title":"Progressive-Hint Prompting Improves Reasoning in Large Language Models","created":"2023-04-19","cited_by_count":147},{"id":"2304.07619","title":"Can ChatGPT Forecast Stock Price Movements? Return Predictability and Large Language Models","created":"2023-04-15","cited_by_count":129},{"id":"1910.10593","title":"Neural Execution of Graph Algorithms","created":"2019-10-23","cited_by_count":121},{"id":"2402.05862","title":"Let Your Graph Do the Talking: Encoding Structured Data for LLMs","created":"2024-02-08","cited_by_count":118},{"id":"2305.13062","title":"Table Meets LLM: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical Study","created":"2023-05-22","cited_by_count":116},{"id":"2310.05845","title":"GraphLLM: Boosting Graph Reasoning Ability of Large Language Model","created":"2023-10-09","cited_by_count":107},{"id":"2205.15659","title":"The CLRS Algorithmic Reasoning Benchmark","created":"2022-05-31","cited_by_count":106},{"id":"2404.18824","title":"Benchmarking Benchmark Leakage in Large Language Models","created":"2024-04-29","cited_by_count":106},{"id":"2105.02761","title":"Neural Algorithmic Reasoning","created":"2021-05-06","cited_by_count":94},{"id":"2310.04668","title":"Label-free Node Classification on Graphs with Large Language Models (LLMS)","created":"2023-10-07","cited_by_count":72},{"id":"2303.12767","title":"Can we trust the evaluation on ChatGPT?","created":"2023-03-22","cited_by_count":63},{"id":"2306.12251","title":"GADBench: Revisiting and Benchmarking Supervised Graph Anomaly Detection","created":"2023-06-21","cited_by_count":58},{"id":"2403.04483","title":"GraphInstruct: Empowering Large Language Models with Graph Understanding and Reasoning Capability","created":"2024-03-07","cited_by_count":58},{"id":"2402.08785","title":"InstructGraph: Boosting Large Language Models via Graph-centric Instruction Tuning and Preference Alignment","created":"2024-02-13","cited_by_count":56},{"id":"2401.08514","title":"Beyond Weisfeiler-Lehman: A Quantitative Framework for GNN Expressiveness","created":"2024-01-16","cited_by_count":39},{"id":"2308.11224","title":"Evaluating Large Language Models on Graphs: Performance Insights and Comparative Analysis","created":"2023-08-22","cited_by_count":35},{"id":"2402.02130","title":"GITA: Graph to Visual and Textual Integration for Vision-Language Graph Reasoning","created":"2024-02-03","cited_by_count":33},{"id":"2402.16029","title":"GraphWiz: An Instruction-Following Language Model for Graph Problems","created":"2024-02-25","cited_by_count":32},{"id":"2302.10258","title":"Neural Algorithmic Reasoning with Causal Regularisation","created":"2023-02-20","cited_by_count":31},{"id":"2405.04950","title":"VisionGraph: Leveraging Large Multimodal Models for Graph Theory Problems in Visual Context","created":"2024-05-08","cited_by_count":31},{"id":"2406.04229","title":"The CLRS-Text Algorithmic Reasoning Language Benchmark","created":"2024-06-06","cited_by_count":28},{"id":"2311.04937","title":"Multimodal Clinical Benchmark for Emergency Care (MC-BEC): A Comprehensive Benchmark for Evaluating Foundation Models in Emergency Medicine","created":"2023-11-07","cited_by_count":24},{"id":"2306.06064","title":"Neural Algorithmic Reasoning for Combinatorial Optimisation","created":"2023-05-18","cited_by_count":19},{"id":"2305.06574","title":"A Fused Gromov-Wasserstein Framework for Unsupervised Knowledge Graph Entity Alignment","created":"2023-05-11","cited_by_count":16},{"id":"2406.09308","title":"Transformers meet Neural Algorithmic Reasoners","created":"2024-06-13","cited_by_count":13},{"id":"2208.11125","title":"Large-scale Entity Alignment via Knowledge Graph Merging, Partitioning and Embedding","created":"2022-08-23","cited_by_count":9},{"id":"2404.03441","title":"Benchmarking ChatGPT on Algorithmic Reasoning","created":"2024-04-04","cited_by_count":8}],"next_cursor":null}