{"total":133,"rows":[{"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":"2302.04023","title":"A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity","created":"2023-02-08","cited_by_count":894,"area":"lr"},{"id":"2210.11610","title":"Large Language Models Can Self-Improve","created":"2022-10-20","cited_by_count":664,"area":"lr"},{"id":"2410.19168","title":"MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark","created":"2024-10-24","cited_by_count":288,"area":"lr"},{"id":"2307.10635","title":"SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models","created":"2023-07-20","cited_by_count":256,"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":"2202.08791","title":"cosFormer: Rethinking Softmax in Attention","created":"2022-02-17","cited_by_count":213,"area":"lr"},{"id":"2304.03439","title":"Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4","created":"2023-04-07","cited_by_count":202,"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":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116,"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":"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":"2309.16298","title":"At Which Training Stage Does Code Data Help LLMs Reasoning?","created":"2023-09-28","cited_by_count":82,"area":"lr"},{"id":"2307.09476","title":"Overthinking the Truth: Understanding how Language Models Process False Demonstrations","created":"2023-07-18","cited_by_count":81,"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":"2406.12753","title":"OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI","created":"2024-06-18","cited_by_count":71,"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":"2506.23719","title":"DABstep: Data Agent Benchmark for Multi-step Reasoning","created":"2025-06-30","cited_by_count":46,"area":"lr"},{"id":"2201.11473","title":"Reasoning Like Program Executors","created":"2022-01-27","cited_by_count":45,"area":"lr"},{"id":"2401.08189","title":"PRewrite: Prompt Rewriting with Reinforcement Learning","created":"2024-01-16","cited_by_count":45,"area":"lr"},{"id":"2405.18634","title":"A Theoretical Understanding of Self-Correction through In-context Alignment","created":"2024-05-28","cited_by_count":44,"area":"lr"},{"id":"2505.05849","title":"AgentVigil: Generic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents","created":"2025-05-09","cited_by_count":42,"area":"lr"},{"id":"2302.04752","title":"Benchmarks for Automated Commonsense Reasoning: A Survey","created":"2023-02-09","cited_by_count":40,"area":"lr"},{"id":"2310.18659","title":"DetermLR: Augmenting LLM-based Logical Reasoning from Indeterminacy to Determinacy","created":"2023-10-28","cited_by_count":34,"area":"lr"},{"id":"2411.02280","title":"The LLM Language Network: A Neuroscientific Approach for Identifying Causally Task-Relevant Units","created":"2024-11-04","cited_by_count":34,"area":"lr"},{"id":"2504.09946","title":"Assessing Judging Bias in Large Reasoning Models: An Empirical Study","created":"2025-04-14","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":"2310.07999","title":"LEMON: Lossless model expansion","created":"2023-10-12","cited_by_count":23,"area":"lr"},{"id":"2405.07551","title":"MuMath-Code: Combining Tool-Use Large Language Models with Multi-perspective Data Augmentation for Mathematical Reasoning","created":"2024-05-13","cited_by_count":22,"area":"lr"},{"id":"2410.11005","title":"Assessing Dialect Fairness and Robustness of Large Language Models in Reasoning Tasks","created":"2024-10-14","cited_by_count":22,"area":"lr"},{"id":"2412.15118","title":"Reasoning Through Execution: Unifying Process and Outcome Rewards for Code Generation","created":"2024-12-19","cited_by_count":21,"area":"lr"},{"id":"2410.04526","title":"FAMMA: A Benchmark for Financial Domain Multilingual Multimodal Question Answering","created":"2024-10-06","cited_by_count":20,"area":"lr"},{"id":"2308.07336","title":"Learning Deductive Reasoning from Synthetic Corpus based on Formal Logic","created":"2023-08-11","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":"2206.01532","title":"Acquiring and Modelling Abstract Commonsense Knowledge via Conceptualization","created":"2022-06-03","cited_by_count":17,"area":"lr"},{"id":"2212.08286","title":"ALERT: Adapting Language Models to Reasoning Tasks","created":"2022-12-16","cited_by_count":17,"area":"lr"},{"id":"2305.07716","title":"Learning to Reason over Scene Graphs: A Case Study of Finetuning GPT-2 into a Robot Language Model for Grounded Task Planning","created":"2023-05-12","cited_by_count":16,"area":"lr"},{"id":"2407.05399","title":"IL-TUR: Benchmark for Indian Legal Text Understanding and Reasoning","created":"2024-07-07","cited_by_count":16,"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":"2502.19587","title":"NeoBERT: A Next-Generation BERT","created":"2025-02-26","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":"2309.10814","title":"Natural Language Embedded Programs for Hybrid Language Symbolic Reasoning","created":"2023-09-19","cited_by_count":15,"area":"lr"},{"id":"2209.14901","title":"DR.BENCH: Diagnostic Reasoning Benchmark for Clinical Natural Language Processing","created":"2022-09-29","cited_by_count":14,"area":"lr"},{"id":"2312.15230","title":"PERP: Rethinking the Prune-Retrain Paradigm in the Era of LLMs","created":"2023-12-23","cited_by_count":14,"area":"lr"},{"id":"2407.08029","title":"A Critical Review of Causal Reasoning Benchmarks for Large Language Models","created":"2024-07-10","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":"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":"2402.03686","title":"Are Machines Better at Complex Reasoning? Unveiling Human-Machine Inference Gaps in Entailment Verification","created":"2024-02-06","cited_by_count":13,"area":"lr"},{"id":"2412.14368","title":"Beyond Math: Stories as a Testbed for Memorization-Constrained Reasoning in LLMs","created":"2024-12-18","cited_by_count":12,"area":"lr"},{"id":"2205.08794","title":"LogiGAN: Learning Logical Reasoning via Adversarial Pre-training","created":"2022-05-18","cited_by_count":11,"area":"lr"},{"id":"2305.12599","title":"Abstract Meaning Representation-Based Logic-Driven Data Augmentation for Logical Reasoning","created":"2023-05-21","cited_by_count":11,"area":"lr"},{"id":"2305.14618","title":"Abductive Commonsense Reasoning Exploiting Mutually Exclusive Explanations","created":"2023-05-24","cited_by_count":11,"area":"lr"},{"id":"2310.13855","title":"Evoke: Evoking Critical Thinking Abilities in LLMs via Reviewer-Author Prompt Editing","created":"2023-10-20","cited_by_count":11,"area":"lr"},{"id":"2505.17406","title":"Robust Answers, Fragile Logic: Probing the Decoupling Hypothesis in LLM Reasoning","created":"2025-05-23","cited_by_count":11,"area":"lr"},{"id":"2402.12091","title":"Do Large Language Models Understand Logic or Just Mimick Context?","created":"2024-02-19","cited_by_count":10,"area":"lr"},{"id":"2406.04215","title":"mCSQA: Multilingual Commonsense Reasoning Dataset with Unified Creation Strategy by Language Models and Humans","created":"2024-06-06","cited_by_count":10,"area":"lr"},{"id":"2308.01684","title":"Baby's CoThought: Leveraging Large Language Models for Enhanced Reasoning in Compact Models","created":"2023-08-03","cited_by_count":9,"area":"lr"},{"id":"2404.07546","title":"Does In-Context Learning Really Learn? Rethinking How Large Language Models Respond and Solve Tasks via In-Context Learning","created":"2024-04-11","cited_by_count":8,"area":"lr"},{"id":"2409.15454","title":"In-Context Learning May Not Elicit Trustworthy Reasoning: A-Not-B Errors in Pretrained Language Models","created":"2024-09-23","cited_by_count":8,"area":"lr"},{"id":"2212.01692","title":"Can In-context Learners Learn a Reasoning Concept from Demonstrations?","created":"2022-12-03","cited_by_count":7,"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":"2505.24181","title":"SCOUT: Teaching Pre-trained Language Models to Enhance Reasoning via Flow Chain-of-Thought","created":"2025-05-30","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":"2405.17062","title":"UniICL: An Efficient Unified Framework Unifying Compression, Selection, and Generation","created":"2024-05-27","cited_by_count":6,"area":"lr"},{"id":"2410.21526","title":"Not All LLM-Generated Data Are Equal: Rethinking Data Weighting in Text Classification","created":"2024-10-28","cited_by_count":6,"area":"lr"},{"id":"2506.02648","title":"Truly Assessing Fluid Intelligence of Large Language Models through Dynamic Reasoning Evaluation","created":"2025-06-03","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":"2212.09282","title":"APOLLO: A Simple Approach for Adaptive Pretraining of Language Models for Logical Reasoning","created":"2022-12-19","cited_by_count":5,"area":"lr"},{"id":"2305.08246","title":"Learning Non-linguistic Skills without Sacrificing Linguistic Proficiency","created":"2023-05-14","cited_by_count":5,"area":"lr"},{"id":"2409.14469","title":"Rethinking Semantic Parsing for Large Language Models: Enhancing LLM Performance with Semantic Hints","created":"2024-09-22","cited_by_count":5,"area":"lr"},{"id":"2501.15627","title":"HardML: A Benchmark For Evaluating Data Science And Machine Learning knowledge and reasoning in AI","created":"2025-01-26","cited_by_count":5,"area":"lr"},{"id":"2505.16686","title":"SPaRC: A Spatial Pathfinding Reasoning Challenge","created":"2025-05-22","cited_by_count":5,"area":"lr"},{"id":"2505.22137","title":"Limited Generalizability in Argument Mining: State-Of-The-Art Models Learn Datasets, Not Arguments","created":"2025-05-28","cited_by_count":5,"area":"lr"},{"id":"2602.19926","title":"Rethinking LoRA for Privacy-Preserving Federated Learning in Large Models","created":"2026-02-23","cited_by_count":5,"area":"lr"},{"id":"2310.05442","title":"Establishing Trustworthiness: Rethinking Tasks and Model Evaluation","created":"2023-10-09","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":"2502.03748","title":"Rethinking Residual Distribution in Locate-then-Edit Model Editing","created":"2025-02-06","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":"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":"2201.01787","title":"Does Entity Abstraction Help Generative Transformers Reason?","created":"2022-01-05","cited_by_count":3,"area":"lr"},{"id":"2210.07519","title":"Can Language Representation Models Think in Bets?","created":"2022-10-14","cited_by_count":3,"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":"2306.15273","title":"IDOL: Indicator-oriented Logic Pre-training for Logical Reasoning","created":"2023-06-27","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":"2501.08641","title":"Reassessing the Role of Chain-of-Thought in Sentiment Analysis: Insights and Limitations","created":"2025-01-15","cited_by_count":3,"area":"lr"},{"id":"2509.17628","title":"MSCoRe: A Benchmark for Multi-Stage Collaborative Reasoning in LLM Agents","created":"2025-09-22","cited_by_count":3,"area":"lr"},{"id":"2510.16276","title":"What Limits Agentic Systems Efficiency?","created":"2025-10-18","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":"2605.03379","title":"Two Calls, Two Moments, and the Vote-Accuracy Curve of Repeated LLM Inference","created":"2026-05-05","cited_by_count":3,"area":"lr"},{"id":"2605.05227","title":"Rethinking Data Curation in LLM Training: Online Reweighting Offers Better Generalization than Offline Methods","created":"2026-04-19","cited_by_count":3,"area":"lr"},{"id":"2207.01450","title":"Discourse-Aware Graph Networks for Textual Logical Reasoning","created":"2022-07-04","cited_by_count":2,"area":"lr"},{"id":"2305.19597","title":"What does the Failure to Reason with \"Respectively\" in Zero/Few-Shot Settings Tell Us about Language Models?","created":"2023-05-31","cited_by_count":2,"area":"lr"},{"id":"2406.15468","title":"MMLU-SR: A Benchmark for Stress-Testing Reasoning Capability of Large Language Models","created":"2024-06-15","cited_by_count":2,"area":"lr"},{"id":"2501.13397","title":"ExLM: Rethinking the Impact of [MASK] Tokens in Masked Language Models","created":"2025-01-23","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"}],"next_cursor":"100"}