{"total":82,"rows":[{"id":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212,"area":"lr"},{"id":"2202.12837","title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?","created":"2022-02-25","cited_by_count":1434,"area":"lr"},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162,"area":"lr"},{"id":"2210.11610","title":"Large Language Models Can Self-Improve","created":"2022-10-20","cited_by_count":664,"area":"lr"},{"id":"2308.11462","title":"LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models","created":"2023-08-20","cited_by_count":336,"area":"lr"},{"id":"2209.00840","title":"FOLIO: Natural Language Reasoning with First-Order Logic","created":"2022-09-02","cited_by_count":235,"area":"lr"},{"id":"2210.07128","title":"Language Models of Code are Few-Shot Commonsense Learners","created":"2022-10-13","cited_by_count":160,"area":"lr"},{"id":"2411.13543","title":"BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games","created":"2024-11-20","cited_by_count":146,"area":"lr"},{"id":"2407.11511","title":"Multi-Step Reasoning with Large Language Models, a Survey","created":"2024-07-16","cited_by_count":143,"area":"lr"},{"id":"2502.19187","title":"BIG-Bench Extra Hard","created":"2025-02-26","cited_by_count":125,"area":"lr"},{"id":"2204.05660","title":"NumGLUE: A Suite of Fundamental yet Challenging Mathematical Reasoning Tasks","created":"2022-04-12","cited_by_count":112,"area":"lr"},{"id":"2312.04350","title":"CLadder: Assessing Causal Reasoning in Language Models","created":"2023-12-07","cited_by_count":107,"area":"lr"},{"id":"2309.17249","title":"Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineering","created":"2023-09-29","cited_by_count":94,"area":"lr"},{"id":"2503.10497","title":"MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation","created":"2025-03-13","cited_by_count":79,"area":"lr"},{"id":"2310.05746","title":"Put Your Money Where Your Mouth Is: Evaluating Strategic Planning and Execution of LLM Agents in an Auction Arena","created":"2023-10-09","cited_by_count":78,"area":"lr"},{"id":"2212.09095","title":"Rethinking the Role of Scale for In-Context Learning: An Interpretability-based Case Study at 66 Billion Scale","created":"2022-12-18","cited_by_count":64,"area":"lr"},{"id":"2303.14725","title":"Natural Language Reasoning, A Survey","created":"2023-03-26","cited_by_count":61,"area":"lr"},{"id":"2310.04928","title":"Large Language Models Only Pass Primary School Exams in Indonesia: A Comprehensive Test on IndoMMLU","created":"2023-10-07","cited_by_count":53,"area":"lr"},{"id":"2305.14106","title":"Better Zero-Shot Reasoning with Self-Adaptive Prompting","created":"2023-05-23","cited_by_count":52,"area":"lr"},{"id":"2310.00836","title":"Towards LogiGLUE: A Brief Survey and A Benchmark for Analyzing Logical Reasoning Capabilities of Language Models","created":"2023-10-02","cited_by_count":35,"area":"lr"},{"id":"2406.09175","title":"ReMI: A Dataset for Reasoning with Multiple Images","created":"2024-06-13","cited_by_count":30,"area":"lr"},{"id":"2301.06627","title":"Dissociating language and thought in large language models","created":"2023-01-16","cited_by_count":29,"area":"lr"},{"id":"2301.11596","title":"ThoughtSource: A central hub for large language model reasoning data","created":"2023-01-27","cited_by_count":23,"area":"lr"},{"id":"2405.00622","title":"Causal Evaluation of Language Models","created":"2024-05-01","cited_by_count":18,"area":"lr"},{"id":"2406.19292","title":"From Artificial Needles to Real Haystacks: Improving Retrieval Capabilities in LLMs by Finetuning on Synthetic Data","created":"2024-06-27","cited_by_count":18,"area":"lr"},{"id":"2501.06254","title":"Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words","created":"2025-01-09","cited_by_count":18,"area":"lr"},{"id":"2212.08286","title":"ALERT: Adapting Language Models to Reasoning Tasks","created":"2022-12-16","cited_by_count":17,"area":"lr"},{"id":"2409.02257","title":"MMLU-Pro+: Evaluating Higher-Order Reasoning and Shortcut Learning in LLMs","created":"2024-09-03","cited_by_count":16,"area":"lr"},{"id":"2305.11662","title":"Separating form and meaning: Using self-consistency to quantify task understanding across multiple senses","created":"2023-05-19","cited_by_count":15,"area":"lr"},{"id":"2209.08141","title":"Psychologically-informed chain-of-thought prompts for metaphor understanding in large language models","created":"2022-09-16","cited_by_count":14,"area":"lr"},{"id":"2409.12929","title":"LogicPro: Improving Complex Logical Reasoning via Program-Guided Learning","created":"2024-09-19","cited_by_count":14,"area":"lr"},{"id":"2506.05587","title":"MMTU: A Massive Multi-Task Table Understanding and Reasoning Benchmark","created":"2025-06-05","cited_by_count":14,"area":"lr"},{"id":"2210.17517","title":"Lila: A Unified Benchmark for Mathematical Reasoning","created":"2022-10-31","cited_by_count":13,"area":"lr"},{"id":"2302.06729","title":"STREET: A Multi-Task Structured Reasoning and Explanation Benchmark","created":"2023-02-13","cited_by_count":13,"area":"lr"},{"id":"2310.09107","title":"GLoRE: Evaluating Logical Reasoning of Large Language Models","created":"2023-10-13","cited_by_count":13,"area":"lr"},{"id":"2506.15455","title":"RE-IMAGINE: Symbolic Benchmark Synthesis for Reasoning Evaluation","created":"2025-06-18","cited_by_count":11,"area":"lr"},{"id":"2310.15239","title":"CRoW: Benchmarking Commonsense Reasoning in Real-World Tasks","created":"2023-10-23","cited_by_count":8,"area":"lr"},{"id":"2502.13119","title":"STEER-ME: Assessing the Microeconomic Reasoning of Large Language Models","created":"2025-02-18","cited_by_count":7,"area":"lr"},{"id":"2202.13529","title":"KMIR: A Benchmark for Evaluating Knowledge Memorization, Identification and Reasoning Abilities of Language Models","created":"2022-02-28","cited_by_count":6,"area":"lr"},{"id":"2303.09427","title":"Logical Implications for Visual Question Answering Consistency","created":"2023-03-16","cited_by_count":6,"area":"lr"},{"id":"2509.03162","title":"SinhalaMMLU: A Comprehensive Benchmark for Evaluating Multitask Language Understanding in Sinhala","created":"2025-09-03","cited_by_count":6,"area":"lr"},{"id":"2511.01650","title":"EngTrace: A Symbolic Benchmark for Verifiable Process Supervision of Engineering Reasoning","created":"2025-11-03","cited_by_count":5,"area":"lr"},{"id":"2209.07000","title":"VIPHY: Probing \"Visible\" Physical Commonsense Knowledge","created":"2022-09-15","cited_by_count":4,"area":"lr"},{"id":"2310.11721","title":"Chain-of-Thought Tuning: Masked Language Models can also Think Step By Step in Natural Language Understanding","created":"2023-10-18","cited_by_count":4,"area":"lr"},{"id":"2505.14354","title":"WirelessMathBench: A Mathematical Modeling Benchmark for LLMs in Wireless Communications","created":"2025-05-20","cited_by_count":4,"area":"lr"},{"id":"2505.15712","title":"TurnaboutLLM: A Deductive Reasoning Benchmark from Detective Games","created":"2025-05-21","cited_by_count":4,"area":"lr"},{"id":"2506.01252","title":"MTCMB: A Multi-Task Benchmark Framework for Evaluating LLMs on Knowledge, Reasoning, and Safety in Traditional Chinese Medicine","created":"2025-06-02","cited_by_count":4,"area":"lr"},{"id":"2511.06346","title":"LPFQA: A Long-Tail Professional Forum-based Benchmark for LLM Evaluation","created":"2025-11-09","cited_by_count":4,"area":"lr"},{"id":"2306.03553","title":"An Approach to Solving the Abstraction and Reasoning Corpus (ARC) Challenge","created":"2023-06-06","cited_by_count":3,"area":"lr"},{"id":"2311.07311","title":"Do large language models and humans have similar behaviors in causal inference with script knowledge?","created":"2023-11-13","cited_by_count":3,"area":"lr"},{"id":"2501.00257","title":"EQUATOR: A Deterministic Framework for Evaluating LLM Reasoning with Open-Ended Questions. # v1.0.0-beta","created":"2024-12-31","cited_by_count":3,"area":"lr"},{"id":"2502.06279","title":"DebateBench: A Challenging Long Context Reasoning Benchmark For Large Language Models","created":"2025-02-10","cited_by_count":3,"area":"lr"},{"id":"2603.12133","title":"TopoBench: Benchmarking LLMs on Hard Topological Reasoning","created":"2026-03-12","cited_by_count":3,"area":"lr"},{"id":"2603.13173","title":"Semantic Invariance in Agentic AI","created":"2026-03-13","cited_by_count":3,"area":"lr"},{"id":"2502.12825","title":"Reasoning and the Trusting Behavior of DeepSeek and GPT: An Experiment Revealing Hidden Fault Lines in Large Language Models","created":"2025-02-18","cited_by_count":2,"area":"lr"},{"id":"2510.13499","title":"ConsintBench: Evaluating Language Models on Real-World Consumer Intent Understanding","created":"2025-10-15","cited_by_count":2,"area":"lr"},{"id":"2603.06428","title":"Abductive Reasoning with Syllogistic Forms in Large Language Models","created":"2026-03-06","cited_by_count":2,"area":"lr"},{"id":"2203.12184","title":"A Theoretically Grounded Benchmark for Evaluating Machine Commonsense","created":"2022-03-23","cited_by_count":1,"area":"lr"},{"id":"2308.04711","title":"Answering Unseen Questions With Smaller Language Models Using Rationale Generation and Dense Retrieval","created":"2023-08-09","cited_by_count":1,"area":"lr"},{"id":"2410.13666","title":"VL-GLUE: A Suite of Fundamental yet Challenging Visuo-Linguistic Reasoning Tasks","created":"2024-10-17","cited_by_count":1,"area":"lr"},{"id":"2412.06975","title":"AutoReason: Automatic Few-Shot Reasoning Decomposition","created":"2024-12-09","cited_by_count":1,"area":"lr"},{"id":"2507.15707","title":"Is Large Language Model Performance on Reasoning Tasks Impacted by Different Ways Questions Are Asked?","created":"2025-07-21","cited_by_count":1,"area":"lr"},{"id":"2508.16697","title":"QueryBandits for Hallucination Mitigation: Exploiting Semantic Features for No-Regret Rewriting","created":"2025-08-22","cited_by_count":1,"area":"lr"},{"id":"2603.14761","title":"BrainBench: Exposing the Commonsense Reasoning Gap in Large Language Models","created":"2026-03-16","cited_by_count":1,"area":"lr"},{"id":"2201.04467","title":"How Does Data Corruption Affect Natural Language Understanding Models? A Study on GLUE datasets","created":"2022-01-12","cited_by_count":0,"area":"lr"},{"id":"2211.13930","title":"TRAC: A Textual Benchmark for Reasoning about Actions and Change","created":"2022-11-25","cited_by_count":0,"area":"lr"},{"id":"2410.18001","title":"Benchmarking Foundation Models on Exceptional Cases: Dataset Creation and Validation","created":"2024-10-23","cited_by_count":0,"area":"lr"},{"id":"2509.00465","title":"Embodied Spatial Intelligence: from Implicit Scene Modeling to Spatial Reasoning","created":"2025-08-30","cited_by_count":0,"area":"lr"},{"id":"2509.09801","title":"HEFT: A Coarse-to-Fine Hierarchy for Enhancing the Efficiency and Accuracy of Language Model Reasoning","created":"2025-09-11","cited_by_count":0,"area":"lr"},{"id":"2511.17290","title":"Estonian WinoGrande Dataset: Comparative Analysis of LLM Performance on Human and Machine Translation","created":"2025-11-21","cited_by_count":0,"area":"lr"},{"id":"2601.03268","title":"WRAVAL -- WRiting Assist eVALuation","created":"2025-12-19","cited_by_count":0,"area":"lr"},{"id":"2601.10581","title":"From Single to Multi-Agent Reasoning: Advancing GeneGPT for Genomics QA","created":"2026-01-15","cited_by_count":0,"area":"lr"},{"id":"2602.20332","title":"No One Size Fits All: QueryBandits for Hallucination Mitigation","created":"2026-02-23","cited_by_count":0,"area":"lr"},{"id":"2603.11687","title":"SemBench: A Universal Semantic Framework for LLM Evaluation","created":"2026-03-12","cited_by_count":0,"area":"lr"},{"id":"2603.17811","title":"Dropout Robustness and Cognitive Profiling of Transformer Models via Stochastic Inference","created":"2026-03-18","cited_by_count":0,"area":"lr"},{"id":"2603.21329","title":"COINBench: Moving Beyond Individual Perspectives to Collective Intent Understanding","created":"2026-03-22","cited_by_count":0,"area":"lr"},{"id":"2605.24573","title":"AstroMind: A High-Fidelity Benchmark for Spacecraft Behavior Reasoning Based on Large Language Models","created":"2026-05-23","cited_by_count":0,"area":"lr"},{"id":"2608.04670","title":"Easy to Complete, Hard to Choose: Investigating LLM Performance on the ProverbIT Benchmark","created":"2026-08-05","cited_by_count":0,"area":"lr"},{"id":"2608.21369","title":"Wazobia Eval: A Benchmark for Nigerian Pidgin Emotion Understanding, Sarcasm Detection, and Cultural Reasoning","created":"2026-06-21","cited_by_count":0,"area":"lr"},{"id":"2609.32431","title":"DualGuard: Dual-Mode Quality Control for Logic-Preserving Data Augmentation","created":"2026-09-26","cited_by_count":0,"area":"lr"},{"id":"2610.03329","title":"SyntaxBench: A Statistical Diagnostic Framework for Character-Level Reasoning in Large Language Models","created":"2026-10-02","cited_by_count":0,"area":"lr"},{"id":"2610.16755","title":"The Multilingual Artificial Hivemind: Do All LLMs Think Alike in Every Language?","created":"2026-10-12","cited_by_count":0,"area":"lr"}],"next_cursor":null}