{"list":"other","total":80,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"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":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"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":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"1809.02789","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","created":"2018-09-08","cited_by_count":2164},{"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":"2406.01574","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","created":"2024-06-03","cited_by_count":1848},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807},{"id":"1808.08745","title":"Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization","created":"2018-08-27","cited_by_count":1317},{"id":"1704.04368","title":"Get To The Point: Summarization with Pointer-Generator Networks","created":"2017-04-14","cited_by_count":1292},{"id":"2311.12983","title":"GAIA: a benchmark for General AI Assistants","created":"2023-11-21","cited_by_count":1128},{"id":"1612.03975","title":"ConceptNet 5.5: An Open Multilingual Graph of General Knowledge","created":"2016-12-12","cited_by_count":1067},{"id":"1506.03340","title":"Teaching Machines to Read and Comprehend","created":"2015-06-10","cited_by_count":1049},{"id":"2201.07207","title":"Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents","created":"2022-01-18","cited_by_count":1035},{"id":"2305.14992","title":"Reasoning with Language Model is Planning with World Model","created":"2023-05-24","cited_by_count":861},{"id":"2501.17161","title":"SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training","created":"2025-01-28","cited_by_count":672},{"id":"2212.10403","title":"Towards Reasoning in Large Language Models: A Survey","created":"2022-12-20","cited_by_count":596},{"id":"1911.12237","title":"SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization","created":"2019-11-27","cited_by_count":535},{"id":"2402.06196","title":"Large Language Models: A Survey","created":"2024-02-09","cited_by_count":525},{"id":"2111.01243","title":"Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey","created":"2021-11-01","cited_by_count":463},{"id":"2003.04807","title":"Efficient Intent Detection with Dual Sentence Encoders","created":"2020-03-10","cited_by_count":433},{"id":"1909.02027","title":"An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction","created":"2019-09-04","cited_by_count":386},{"id":"2206.10498","title":"PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change","created":"2022-06-21","cited_by_count":382},{"id":"2403.07718","title":"WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?","created":"2024-03-12","cited_by_count":363},{"id":"2106.13822","title":"XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages","created":"2021-06-25","cited_by_count":347},{"id":"2412.14161","title":"TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks","created":"2024-12-18","cited_by_count":326},{"id":"2502.03373","title":"Demystifying Long Chain-of-Thought Reasoning in LLMs","created":"2025-02-05","cited_by_count":326},{"id":"2501.09686","title":"Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models","created":"2025-01-16","cited_by_count":293},{"id":"2410.08146","title":"Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning","created":"2024-10-10","cited_by_count":279},{"id":"2310.02226","title":"Think before you speak: Training Language Models With Pause Tokens","created":"2023-10-03","cited_by_count":264},{"id":"2402.12875","title":"Chain of Thought Empowers Transformers to Solve Inherently Serial Problems","created":"2024-02-20","cited_by_count":260},{"id":"2212.09597","title":"Reasoning with Language Model Prompting: A Survey","created":"2022-12-19","cited_by_count":252},{"id":"2404.15758","title":"Let's Think Dot by Dot: Hidden Computation in Transformer Language Models","created":"2024-04-24","cited_by_count":191},{"id":"2105.06762","title":"DialogSum: A Real-Life Scenario Dialogue Summarization Dataset","created":"2021-05-14","cited_by_count":183},{"id":"2010.03093","title":"WikiLingua: A New Benchmark Dataset for Cross-Lingual Abstractive Summarization","created":"2020-10-07","cited_by_count":154},{"id":"2310.10634","title":"OpenAgents: An Open Platform for Language Agents in the Wild","created":"2023-10-16","cited_by_count":137},{"id":"2310.01714","title":"Large Language Models as Analogical Reasoners","created":"2023-10-03","cited_by_count":107},{"id":"2407.05291","title":"WorkArena++: Towards Compositional Planning and Reasoning-based Common Knowledge Work Tasks","created":"2024-07-07","cited_by_count":90},{"id":"2401.03205","title":"The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models","created":"2024-01-06","cited_by_count":88},{"id":"2401.17167","title":"Planning, Creation, Usage: Benchmarking LLMs for Comprehensive Tool Utilization in Real-World Complex Scenarios","created":"2024-01-30","cited_by_count":86},{"id":"2402.09205","title":"Tell Me More! Towards Implicit User Intention Understanding of Language Model Driven Agents","created":"2024-02-14","cited_by_count":74},{"id":"2312.11562","title":"A Survey of Reasoning with Foundation Models","created":"2023-12-17","cited_by_count":70},{"id":"2405.14205","title":"Agent Planning with World Knowledge Model","created":"2024-05-23","cited_by_count":70},{"id":"2012.08987","title":"Discovering New Intents with Deep Aligned Clustering","created":"2020-12-16","cited_by_count":68},{"id":"2303.14725","title":"Natural Language Reasoning, A Survey","created":"2023-03-26","cited_by_count":61},{"id":"2310.05707","title":"Guiding Language Model Reasoning with Planning Tokens","created":"2023-10-09","cited_by_count":58},{"id":"2502.09100","title":"Logical Reasoning in Large Language Models: A Survey","created":"2025-02-13","cited_by_count":55},{"id":"2403.15452","title":"What Are Tools Anyway? A Survey from the Language Model Perspective","created":"2024-03-18","cited_by_count":54},{"id":"2412.16145","title":"Offline Reinforcement Learning for LLM Multi-Step Reasoning","created":"2024-12-20","cited_by_count":54},{"id":"2502.03461","title":"Do Large Language Model Benchmarks Test Reliability?","created":"2025-02-05","cited_by_count":54},{"id":"2502.15652","title":"Empowering LLMs with Logical Reasoning: A Comprehensive Survey","created":"2025-02-21","cited_by_count":51},{"id":"2402.00658","title":"Learning Planning-based Reasoning by Trajectories Collection and Process Reward Synthesizing","created":"2024-02-01","cited_by_count":49},{"id":"2402.10890","title":"When is Tree Search Useful for LLM Planning? It Depends on the Discriminator","created":"2024-02-16","cited_by_count":47},{"id":"2502.03671","title":"Advancing Reasoning in Large Language Models: Promising Methods and Approaches","created":"2025-02-05","cited_by_count":43},{"id":"2406.03807","title":"Tool-Planner: Task Planning with Clusters across Multiple Tools","created":"2024-06-06","cited_by_count":33},{"id":"2409.14826","title":"ToolPlanner: A Tool Augmented LLM for Multi Granularity Instructions with Path Planning and Feedback","created":"2024-09-23","cited_by_count":29},{"id":"2410.19743","title":"AppBench: Planning of Multiple APIs from Various APPs for Complex User Instruction","created":"2024-10-10","cited_by_count":24},{"id":"2405.09220","title":"ALPINE: Unveiling the Planning Capability of Autoregressive Learning in Language Models","created":"2024-05-15","cited_by_count":18},{"id":"2404.13940","title":"A User-Centric Multi-Intent Benchmark for Evaluating Large Language Models","created":"2024-04-22","cited_by_count":15},{"id":"2502.18331","title":"BottleHumor: Self-Informed Humor Explanation using the Information Bottleneck Principle","created":"2025-02-22","cited_by_count":6},{"id":"2403.18277","title":"BlendX: Complex Multi-Intent Detection with Blended Patterns","created":"2024-03-27","cited_by_count":4},{"id":"2403.04314","title":"Can Your Model Tell a Negation from an Implicature? Unravelling Challenges With Intent Encoders","created":"2024-03-07","cited_by_count":2},{"id":"2406.03127","title":"Towards Real-world Scenario: Imbalanced New Intent Discovery","created":"2024-06-05","cited_by_count":2},{"id":"2502.04689","title":"Improving Language Models with Intentional Analysis","created":"2025-02-07","cited_by_count":2}],"next_cursor":null}