{"total":217,"rows":[{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879,"area":null},{"id":"2308.14132","title":"Detecting Language Model Attacks with Perplexity","created":"2023-08-27","cited_by_count":431,"area":"safety"},{"id":"2308.16884","title":"The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants","created":"2023-08-31","cited_by_count":311,"area":null},{"id":"2212.09561","title":"Large Language Models are Better Reasoners with Self-Verification","created":"2022-12-19","cited_by_count":307,"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":"2206.02336","title":"Making Large Language Models Better Reasoners with Step-Aware Verifier","created":"2022-06-06","cited_by_count":233,"area":"lr"},{"id":"2409.05907","title":"Programming Refusal with Conditional Activation Steering","created":"2024-09-06","cited_by_count":206,"area":"mechinterp"},{"id":"2404.02078","title":"Advancing LLM Reasoning Generalists with Preference Trees","created":"2024-04-02","cited_by_count":192,"area":"lr"},{"id":"2309.15402","title":"Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future","created":"2023-09-27","cited_by_count":184,"area":"lr"},{"id":"2302.12246","title":"Active Prompting with Chain-of-Thought for Large Language Models","created":"2023-02-23","cited_by_count":154,"area":"lr"},{"id":"2308.07317","title":"Platypus: Quick, Cheap, and Powerful Refinement of LLMs","created":"2023-08-14","cited_by_count":150,"area":null},{"id":"2305.08455","title":"Document Understanding Dataset and Evaluation (DUDE)","created":"2023-05-15","cited_by_count":135,"area":null},{"id":"2503.05179","title":"Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching","created":"2025-03-07","cited_by_count":117,"area":"lr"},{"id":"2205.11502","title":"On the Paradox of Learning to Reason from Data","created":"2022-05-23","cited_by_count":93,"area":"lr"},{"id":"2107.12708","title":"QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension","created":"2021-07-27","cited_by_count":91,"area":null},{"id":"2503.00031","title":"Efficient Test-Time Scaling via Self-Calibration","created":"2025-02-25","cited_by_count":75,"area":"lr"},{"id":"2411.00855","title":"Vision-Language Models Can Self-Improve Reasoning via Reflection","created":"2024-10-30","cited_by_count":69,"area":"lr"},{"id":"2404.15522","title":"LogicBench: Towards Systematic Evaluation of Logical Reasoning Ability of Large Language Models","created":"2024-04-23","cited_by_count":68,"area":"lr"},{"id":"2209.08199","title":"ScreenQA: Large-Scale Question-Answer Pairs over Mobile App Screenshots","created":"2022-09-16","cited_by_count":66,"area":null},{"id":"2306.09841","title":"Are Large Language Models Really Good Logical Reasoners? A Comprehensive Evaluation and Beyond","created":"2023-06-16","cited_by_count":65,"area":"lr"},{"id":"2406.14491","title":"Instruction Pre-Training: Language Models are Supervised Multitask Learners","created":"2024-06-20","cited_by_count":63,"area":null},{"id":"2303.14725","title":"Natural Language Reasoning, A Survey","created":"2023-03-26","cited_by_count":61,"area":"lr"},{"id":"2503.23077","title":"Efficient Inference for Large Reasoning Models: A Survey","created":"2025-03-29","cited_by_count":61,"area":"lr"},{"id":"2305.15541","title":"Harnessing the Power of Large Language Models for Natural Language to First-Order Logic Translation","created":"2023-05-24","cited_by_count":59,"area":"alignment"},{"id":"2202.12359","title":"UnifiedQA-v2: Stronger Generalization via Broader Cross-Format Training","created":"2022-02-23","cited_by_count":57,"area":null},{"id":"2305.19555","title":"Large Language Models Are Not Strong Abstract Reasoners","created":"2023-05-31","cited_by_count":53,"area":"lr"},{"id":"2104.06598","title":"AR-LSAT: Investigating Analytical Reasoning of Text","created":"2021-04-14","cited_by_count":51,"area":null},{"id":"2502.15652","title":"Empowering LLMs with Logical Reasoning: A Comprehensive Survey","created":"2025-02-21","cited_by_count":51,"area":"lr"},{"id":"2305.11499","title":"RCOT: Detecting and Rectifying Factual Inconsistency in Reasoning by Reversing Chain-of-Thought","created":"2023-05-19","cited_by_count":47,"area":"lr"},{"id":"2502.19411","title":"Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs","created":"2025-02-26","cited_by_count":47,"area":"lr"},{"id":"2105.03659","title":"Logic-Driven Context Extension and Data Augmentation for Logical Reasoning of Text","created":"2021-05-08","cited_by_count":46,"area":null},{"id":"2201.11473","title":"Reasoning Like Program Executors","created":"2022-01-27","cited_by_count":45,"area":"lr"},{"id":"2108.00648","title":"From LSAT: The Progress and Challenges of Complex Reasoning","created":"2021-08-02","cited_by_count":43,"area":null},{"id":"2301.11333","title":"Knowing About Knowing: An Illusion of Human Competence Can Hinder Appropriate Reliance on AI Systems","created":"2023-01-25","cited_by_count":41,"area":null},{"id":"2404.04735","title":"MACM: Utilizing a Multi-Agent System for Condition Mining in Solving Complex Mathematical Problems","created":"2024-04-06","cited_by_count":41,"area":"lr"},{"id":"2304.08979","title":"In ChatGPT We Trust? Measuring and Characterizing the Reliability of ChatGPT","created":"2023-04-18","cited_by_count":37,"area":null},{"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":"2109.06427","title":"Commonsense-Focused Dialogues for Response Generation: An Empirical Study","created":"2021-09-14","cited_by_count":30,"area":null},{"id":"2301.12307","title":"MQAG: Multiple-choice Question Answering and Generation for Assessing Information Consistency in Summarization","created":"2023-01-28","cited_by_count":30,"area":null},{"id":"2408.00114","title":"Inductive or Deductive? Rethinking the Fundamental Reasoning Abilities of LLMs","created":"2024-07-31","cited_by_count":29,"area":"lr"},{"id":"2411.12498","title":"Enhancing Reasoning Capabilities of LLMs via Principled Synthetic Logic Corpus","created":"2024-11-19","cited_by_count":29,"area":"lr"},{"id":"2103.14349","title":"DAGN: Discourse-Aware Graph Network for Logical Reasoning","created":"2021-03-26","cited_by_count":28,"area":null},{"id":"2104.08825","title":"Flexible Generation of Natural Language Deductions","created":"2021-04-18","cited_by_count":28,"area":null},{"id":"2203.08480","title":"E-KAR: A Benchmark for Rationalizing Natural Language Analogical Reasoning","created":"2022-03-16","cited_by_count":28,"area":"lr"},{"id":"2504.18838","title":"Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks","created":"2025-04-26","cited_by_count":28,"area":null},{"id":"2509.24803","title":"TimeOmni-1: Incentivizing Complex Reasoning with Time Series in Large Language Models","created":"2025-09-29","cited_by_count":27,"area":null},{"id":"2101.10421","title":"English Machine Reading Comprehension Datasets: A Survey","created":"2021-01-25","cited_by_count":26,"area":null},{"id":"2312.02143","title":"Competition-Level Problems are Effective LLM Evaluators","created":"2023-12-04","cited_by_count":25,"area":"lr"},{"id":"2402.01512","title":"Distractor Generation in Multiple-Choice Tasks: A Survey of Methods, Datasets, and Evaluation","created":"2024-02-02","cited_by_count":25,"area":null},{"id":"2409.03563","title":"100 instances is all you need: predicting the success of a new LLM on unseen data by testing on a few instances","created":"2024-09-05","cited_by_count":24,"area":null},{"id":"2504.08672","title":"Genius: A Generalizable and Purely Unsupervised Self-Training Framework For Advanced Reasoning","created":"2025-04-11","cited_by_count":24,"area":"lr"},{"id":"2206.15030","title":"Modern Question Answering Datasets and Benchmarks: A Survey","created":"2022-06-30","cited_by_count":23,"area":null},{"id":"2209.11830","title":"Multiple-Choice Question Generation: Towards an Automated Assessment Framework","created":"2022-09-23","cited_by_count":23,"area":null},{"id":"2409.17539","title":"Logic-of-Thought: Injecting Logic into Contexts for Full Reasoning in Large Language Models","created":"2024-09-26","cited_by_count":23,"area":"lr"},{"id":"2410.03136","title":"Deliberate Reasoning in Language Models as Structure-Aware Planning with an Accurate World Model","created":"2024-10-04","cited_by_count":23,"area":"wm"},{"id":"2203.00357","title":"MERIt: Meta-Path Guided Contrastive Learning for Logical Reasoning","created":"2022-03-01","cited_by_count":22,"area":"lr"},{"id":"2205.12598","title":"RobustLR: Evaluating Robustness to Logical Perturbation in Deductive Reasoning","created":"2022-05-25","cited_by_count":22,"area":"lr"},{"id":"2501.14851","title":"JustLogic: A Comprehensive Benchmark for Evaluating Deductive Reasoning in Large Language Models","created":"2025-01-24","cited_by_count":22,"area":"lr"},{"id":"2307.01640","title":"Chain of Thought Prompting Elicits Knowledge Augmentation","created":"2023-07-04","cited_by_count":21,"area":"lr"},{"id":"2312.04333","title":"Is Bigger and Deeper Always Better? Probing LLaMA Across Scales and Layers","created":"2023-12-07","cited_by_count":20,"area":null},{"id":"2505.15801","title":"VerifyBench: Benchmarking Reference-based Reward Systems for Large Language Models","created":"2025-05-21","cited_by_count":20,"area":"lr"},{"id":"2310.12342","title":"Eliminating Reasoning via Inferring with Planning: A New Framework to Guide LLMs' Non-linear Thinking","created":"2023-10-18","cited_by_count":19,"area":"lr"},{"id":"2406.13094","title":"Exploring and Benchmarking the Planning Capabilities of Large Language Models","created":"2024-06-18","cited_by_count":19,"area":null},{"id":"2408.15778","title":"LogicGame: Benchmarking Rule-Based Reasoning Abilities of Large Language Models","created":"2024-08-28","cited_by_count":19,"area":"lr"},{"id":"2509.17995","title":"Variation in Verification: Understanding Verification Dynamics in Large Language Models","created":"2025-09-22","cited_by_count":19,"area":null},{"id":"2410.02108","title":"ReGenesis: LLMs can Grow into Reasoning Generalists via Self-Improvement","created":"2024-10-03","cited_by_count":18,"area":"lr"},{"id":"2211.01482","title":"RQUGE: Reference-Free Metric for Evaluating Question Generation by Answering the Question","created":"2022-11-02","cited_by_count":17,"area":null},{"id":"2405.04086","title":"Optimizing Language Model's Reasoning Abilities with Weak Supervision","created":"2024-05-07","cited_by_count":15,"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":"2310.09107","title":"GLoRE: Evaluating Logical Reasoning of Large Language Models","created":"2023-10-13","cited_by_count":13,"area":"lr"},{"id":"2503.13288","title":"$\\phi$-Decoding: Adaptive Foresight Sampling for Balanced Inference-Time Exploration and Exploitation","created":"2025-03-17","cited_by_count":13,"area":"lr"},{"id":"2311.05419","title":"Mirror: A Universal Framework for Various Information Extraction Tasks","created":"2023-11-09","cited_by_count":12,"area":null},{"id":"2404.04293","title":"Reason from Fallacy: Enhancing Large Language Models' Logical Reasoning through Logical Fallacy Understanding","created":"2024-04-04","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":"2210.06104","title":"EduQG: A Multi-format Multiple Choice Dataset for the Educational Domain","created":"2022-10-12","cited_by_count":11,"area":null},{"id":"2301.05948","title":"tasksource: A Dataset Harmonization Framework for Streamlined NLP Multi-Task Learning and Evaluation","created":"2023-01-14","cited_by_count":11,"area":null},{"id":"2306.08997","title":"Exploring the MIT Mathematics and EECS Curriculum Using Large Language Models","created":"2023-06-15","cited_by_count":10,"area":null},{"id":"2403.10351","title":"TriSum: Learning Summarization Ability from Large Language Models with Structured Rationale","created":"2024-03-15","cited_by_count":10,"area":null},{"id":"2410.02229","title":"CodePMP: Scalable Preference Model Pretraining for Large Language Model Reasoning","created":"2024-10-03","cited_by_count":10,"area":"lr"},{"id":"2502.09642","title":"Krutrim LLM: Multilingual Foundational Model for over a Billion People","created":"2025-02-10","cited_by_count":10,"area":null},{"id":"2205.00274","title":"Clues Before Answers: Generation-Enhanced Multiple-Choice QA","created":"2022-04-30","cited_by_count":9,"area":null},{"id":"2205.10714","title":"Interpretable Proof Generation via Iterative Backward Reasoning","created":"2022-05-22","cited_by_count":9,"area":"lr"},{"id":"2211.16220","title":"Which Shortcut Solution Do Question Answering Models Prefer to Learn?","created":"2022-11-29","cited_by_count":9,"area":null},{"id":"2407.03545","title":"On Evaluating Explanation Utility for Human-AI Decision Making in NLP","created":"2024-07-03","cited_by_count":9,"area":null},{"id":"2410.07035","title":"PositionID: LLMs can Control Lengths, Copy and Paste with Explicit Positional Awareness","created":"2024-10-09","cited_by_count":9,"area":"lr"},{"id":"2502.15823","title":"InductionBench: LLMs Fail in the Simplest Complexity Class","created":"2025-02-20","cited_by_count":9,"area":null},{"id":"2505.13346","title":"J4R: Learning to Judge with Equivalent Initial State Group Relative Policy Optimization","created":"2025-05-19","cited_by_count":9,"area":"lr"},{"id":"2505.22830","title":"What Has Been Lost with Synthetic Evaluation?","created":"2025-05-28","cited_by_count":9,"area":null},{"id":"2203.08992","title":"AdaLoGN: Adaptive Logic Graph Network for Reasoning-Based Machine Reading Comprehension","created":"2022-03-16","cited_by_count":8,"area":"lr"},{"id":"2205.00731","title":"Logiformer: A Two-Branch Graph Transformer Network for Interpretable Logical Reasoning","created":"2022-05-02","cited_by_count":8,"area":"lr"},{"id":"2305.13718","title":"Exploring Self-supervised Logic-enhanced Training for Large Language Models","created":"2023-05-23","cited_by_count":8,"area":"lr"},{"id":"2306.04031","title":"Certified Deductive Reasoning with Language Models","created":"2023-06-06","cited_by_count":8,"area":"lr"},{"id":"2305.06557","title":"Long-Tailed Question Answering in an Open World","created":"2023-05-11","cited_by_count":7,"area":null},{"id":"2306.13047","title":"Analysis of the Cambridge Multiple-Choice Questions Reading Dataset with a Focus on Candidate Response Distribution","created":"2023-06-22","cited_by_count":7,"area":null},{"id":"2310.05450","title":"Empower Nested Boolean Logic via Self-Supervised Curriculum Learning","created":"2023-10-09","cited_by_count":7,"area":"lr"},{"id":"2311.17438","title":"CLOMO: Counterfactual Logical Modification with Large Language Models","created":"2023-11-29","cited_by_count":7,"area":"lr"},{"id":"2401.05787","title":"Chain of Evidences and Evidence to Generate: Prompting for Context Grounded and Retrieval Augmented Reasoning","created":"2024-01-11","cited_by_count":7,"area":"lr"},{"id":"2505.11854","title":"Evaluating the Logical Reasoning Abilities of Large Reasoning Models","created":"2025-05-17","cited_by_count":7,"area":"lr"},{"id":"2510.05164","title":"SATER: A Self-Aware and Token-Efficient Approach to Routing and Cascading","created":"2025-10-04","cited_by_count":7,"area":null},{"id":"2511.01365","title":"The Ouroboros of Benchmarking: Reasoning Evaluation in an Era of Saturation","created":"2025-11-03","cited_by_count":7,"area":"lr"}],"next_cursor":"100"}