{"total":162,"rows":[{"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":"2302.00093","title":"Large Language Models Can Be Easily Distracted by Irrelevant Context","created":"2023-01-31","cited_by_count":841,"area":null},{"id":"2305.19466","title":"The Impact of Positional Encoding on Length Generalization in Transformers","created":"2023-05-31","cited_by_count":327,"area":null},{"id":"2301.13379","title":"Faithful Chain-of-Thought Reasoning","created":"2023-01-31","cited_by_count":288,"area":"lr"},{"id":"2212.09597","title":"Reasoning with Language Model Prompting: A Survey","created":"2022-12-19","cited_by_count":252,"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":"2305.09656","title":"SatLM: Satisfiability-Aided Language Models Using Declarative Prompting","created":"2023-05-16","cited_by_count":102,"area":"lr"},{"id":"2309.17167","title":"DyVal: Dynamic Evaluation of Large Language Models for Reasoning Tasks","created":"2023-09-29","cited_by_count":101,"area":"lr"},{"id":"2210.03050","title":"State-of-the-art generalisation research in NLP: A taxonomy and review","created":"2022-10-06","cited_by_count":98,"area":null},{"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":"2107.02794","title":"Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoning","created":"2021-07-06","cited_by_count":85,"area":null},{"id":"2305.15269","title":"Testing the General Deductive Reasoning Capacity of Large Language Models Using OOD Examples","created":"2023-05-24","cited_by_count":84,"area":"lr"},{"id":"2402.11443","title":"Benchmark Self-Evolving: A Multi-Agent Framework for Dynamic LLM Evaluation","created":"2024-02-18","cited_by_count":75,"area":"agents"},{"id":"2402.13904","title":"Calibrating Large Language Models with Sample Consistency","created":"2024-02-21","cited_by_count":73,"area":null},{"id":"2306.07303","title":"A Comprehensive Survey on Applications of Transformers for Deep Learning Tasks","created":"2023-06-11","cited_by_count":71,"area":null},{"id":"2310.07064","title":"Large Language Models can Learn Rules","created":"2023-10-10","cited_by_count":69,"area":null},{"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":"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":"2304.04812","title":"Scallop: A Language for Neurosymbolic Programming","created":"2023-04-10","cited_by_count":63,"area":"lr"},{"id":"2303.14725","title":"Natural Language Reasoning, A Survey","created":"2023-03-26","cited_by_count":61,"area":"lr"},{"id":"2307.07696","title":"Coupling Large Language Models with Logic Programming for Robust and General Reasoning from Text","created":"2023-07-15","cited_by_count":59,"area":"lr"},{"id":"2406.01563","title":"LoFiT: Localized Fine-tuning on LLM Representations","created":"2024-06-03","cited_by_count":57,"area":null},{"id":"2205.12443","title":"Generating Natural Language Proofs with Verifier-Guided Search","created":"2022-05-25","cited_by_count":52,"area":null},{"id":"2306.07934","title":"BoardgameQA: A Dataset for Natural Language Reasoning with Contradictory Information","created":"2023-06-13","cited_by_count":44,"area":"lr"},{"id":"2410.23856","title":"Can Language Models Perform Robust Reasoning in Chain-of-thought Prompting with Noisy Rationales?","created":"2024-10-31","cited_by_count":41,"area":"lr"},{"id":"2112.00578","title":"Systematic Generalization with Edge Transformers","created":"2021-12-01","cited_by_count":38,"area":null},{"id":"2207.10430","title":"The Neural Race Reduction: Dynamics of Abstraction in Gated Networks","created":"2022-07-21","cited_by_count":37,"area":null},{"id":"2406.06467","title":"How Far Can Transformers Reason? The Globality Barrier and Inductive Scratchpad","created":"2024-06-10","cited_by_count":36,"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":"2112.11941","title":"CRASS: A Novel Data Set and Benchmark to Test Counterfactual Reasoning of Large Language Models","created":"2021-12-22","cited_by_count":34,"area":null},{"id":"2212.10923","title":"Language Models as Inductive Reasoners","created":"2022-12-21","cited_by_count":32,"area":"lr"},{"id":"2409.13724","title":"Logically Consistent Language Models via Neuro-Symbolic Integration","created":"2024-09-09","cited_by_count":30,"area":null},{"id":"2203.10261","title":"FaiRR: Faithful and Robust Deductive Reasoning over Natural Language","created":"2022-03-19","cited_by_count":29,"area":"lr"},{"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":"2402.11442","title":"Can LLMs Reason with Rules? Logic Scaffolding for Stress-Testing and Improving LLMs","created":"2024-02-18","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":"2312.02143","title":"Competition-Level Problems are Effective LLM Evaluators","created":"2023-12-04","cited_by_count":25,"area":"lr"},{"id":"2406.05183","title":"The Factorization Curse: Which Tokens You Predict Underlie the Reversal Curse and More","created":"2024-06-07","cited_by_count":25,"area":null},{"id":"2506.18582","title":"Parallel Continuous Chain-of-Thought with Jacobi Iteration","created":"2025-06-23","cited_by_count":25,"area":"lr"},{"id":"2407.08440","title":"Beyond Instruction Following: Evaluating Inferential Rule Following of Large Language Models","created":"2024-07-11","cited_by_count":23,"area":null},{"id":"2506.08295","title":"From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?","created":"2025-06-09","cited_by_count":23,"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":"2308.09267","title":"GraphReason: Enhancing Reasoning Capabilities of Large Language Models through A Graph-Based Verification Approach","created":"2023-08-18","cited_by_count":21,"area":"lr"},{"id":"2303.03581","title":"Neural Compositional Rule Learning for Knowledge Graph Reasoning","created":"2023-03-07","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":"2405.03146","title":"Quantifying the Capabilities of LLMs across Scale and Precision","created":"2024-05-06","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":"2112.09054","title":"Pushing the Limits of Rule Reasoning in Transformers through Natural Language Satisfiability","created":"2021-12-16","cited_by_count":18,"area":null},{"id":"2205.11432","title":"Logical Reasoning with Span-Level Predictions for Interpretable and Robust NLI Models","created":"2022-05-23","cited_by_count":18,"area":"lr"},{"id":"2305.03742","title":"Improved Logical Reasoning of Language Models via Differentiable Symbolic Programming","created":"2023-05-05","cited_by_count":18,"area":"lr"},{"id":"2305.06349","title":"RECKONING: Reasoning through Dynamic Knowledge Encoding","created":"2023-05-10","cited_by_count":18,"area":"lr"},{"id":"2408.13654","title":"Symbolic Working Memory Enhances Language Models for Complex Rule Application","created":"2024-08-24","cited_by_count":17,"area":"lr"},{"id":"2406.00252","title":"Towards Rationality in Language and Multimodal Agents: A Survey","created":"2024-06-01","cited_by_count":16,"area":"agents"},{"id":"2101.10713","title":"Exploring Transitivity in Neural NLI Models through Veridicality","created":"2021-01-26","cited_by_count":15,"area":null},{"id":"2103.13033","title":"Thinking Aloud: Dynamic Context Generation Improves Zero-Shot Reasoning Performance of GPT-2","created":"2021-03-24","cited_by_count":15,"area":null},{"id":"2405.15302","title":"Understanding the Language Model to Solve the Symbolic Multi-Step Reasoning Problem from the Perspective of Buffer Mechanism","created":"2024-05-24","cited_by_count":15,"area":"lr"},{"id":"2406.08787","title":"A Survey on Compositional Learning of AI Models: Theoretical and Experimental Practices","created":"2024-06-13","cited_by_count":15,"area":null},{"id":"2402.13415","title":"Structure Guided Prompt: Instructing Large Language Model in Multi-Step Reasoning by Exploring Graph Structure of the Text","created":"2024-02-20","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":"2502.20377","title":"PhantomWiki: On-Demand Datasets for Reasoning and Retrieval Evaluation","created":"2025-02-27","cited_by_count":14,"area":"lr"},{"id":"2504.01001","title":"Zero-shot Benchmarking: A Framework for Flexible and Scalable Automatic Evaluation of Language Models","created":"2025-04-01","cited_by_count":14,"area":null},{"id":"2110.08542","title":"Hey AI, Can You Solve Complex Tasks by Talking to Agents?","created":"2021-10-16","cited_by_count":13,"area":null},{"id":"2302.06729","title":"STREET: A Multi-Task Structured Reasoning and Explanation Benchmark","created":"2023-02-13","cited_by_count":13,"area":"lr"},{"id":"2203.15099","title":"LogicInference: A New Dataset for Teaching Logical Inference to seq2seq Models","created":"2022-03-28","cited_by_count":12,"area":null},{"id":"2308.07902","title":"Through the Lens of Core Competency: Survey on Evaluation of Large Language Models","created":"2023-08-15","cited_by_count":12,"area":null},{"id":"2501.19215","title":"Strassen Attention, Split VC Dimension and Compositionality in Transformers","created":"2025-01-31","cited_by_count":12,"area":null},{"id":"2409.12437","title":"Enhancing Logical Reasoning in Large Language Models through Graph-based Synthetic Data","created":"2024-09-19","cited_by_count":8,"area":"lr"},{"id":"2106.01077","title":"SyGNS: A Systematic Generalization Testbed Based on Natural Language Semantics","created":"2021-06-02","cited_by_count":7,"area":null},{"id":"2112.00086","title":"Dyna-bAbI: unlocking bAbI's potential with dynamic synthetic benchmarking","created":"2021-11-30","cited_by_count":7,"area":null},{"id":"2205.06454","title":"R5: Rule Discovery with Reinforced and Recurrent Relational Reasoning","created":"2022-05-13","cited_by_count":7,"area":null},{"id":"2410.11900","title":"FLARE: Faithful Logic-Aided Reasoning and Exploration","created":"2024-10-14","cited_by_count":7,"area":"lr"},{"id":"2412.14515","title":"Relational Programming with Foundation Models","created":"2024-12-19","cited_by_count":7,"area":null},{"id":"2505.11854","title":"Evaluating the Logical Reasoning Abilities of Large Reasoning Models","created":"2025-05-17","cited_by_count":7,"area":"lr"},{"id":"2012.01365","title":"DERAIL: Diagnostic Environments for Reward And Imitation Learning","created":"2020-12-02","cited_by_count":6,"area":"offlinerl"},{"id":"2211.07950","title":"Breakpoint Transformers for Modeling and Tracking Intermediate Beliefs","created":"2022-11-15","cited_by_count":6,"area":null},{"id":"2503.01544","title":"Compositional Reasoning with Transformers, RNNs, and Chain of Thought","created":"2025-03-03","cited_by_count":6,"area":"lr"},{"id":"2504.02810","title":"Generative Evaluation of Complex Reasoning in Large Language Models","created":"2025-04-03","cited_by_count":6,"area":"lr"},{"id":"2505.17225","title":"Reasoning Model is Stubborn: Diagnosing Instruction Overriding in Reasoning Models","created":"2025-05-22","cited_by_count":6,"area":"lr"},{"id":"2506.08672","title":"RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling","created":"2025-06-10","cited_by_count":6,"area":"lr"},{"id":"2202.04161","title":"Logical Reasoning for Task Oriented Dialogue Systems","created":"2022-02-08","cited_by_count":5,"area":"lr"},{"id":"2208.00329","title":"PASTA: A Dataset for Modeling Participant States in Narratives","created":"2022-07-31","cited_by_count":5,"area":null},{"id":"2212.05093","title":"Plug-and-Play Recipe Generation with Content Planning","created":"2022-12-09","cited_by_count":5,"area":null},{"id":"2302.09458","title":"Learning Language Representations with Logical Inductive Bias","created":"2023-02-19","cited_by_count":5,"area":null},{"id":"2410.01600","title":"ENTP: Encoder-only Next Token Prediction","created":"2024-10-02","cited_by_count":5,"area":null},{"id":"2410.03348","title":"Dolphin: A Programmable Framework for Scalable Neurosymbolic Learning","created":"2024-10-04","cited_by_count":5,"area":"lr"},{"id":"2407.17396","title":"Systematic Relational Reasoning With Epistemic Graph Neural Networks","created":"2024-07-24","cited_by_count":4,"area":null},{"id":"2502.15335","title":"Stepwise Informativeness Search for Efficient and Effective LLM Reasoning","created":"2025-02-21","cited_by_count":4,"area":"lr"},{"id":"2505.24874","title":"The Road to Generalizable Neuro-Symbolic Learning Should be Paved with Foundation Models","created":"2025-05-30","cited_by_count":4,"area":null},{"id":"2508.03366","title":"A Comparative Study of Neurosymbolic AI Approaches to Interpretable Logical Reasoning","created":"2025-08-05","cited_by_count":4,"area":"lr"},{"id":"2509.16590","title":"Question Answering with LLMs and Learning from Answer Sets","created":"2025-09-20","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":"2403.18327","title":"$\\forall$uto$\\exists$val: Autonomous Assessment of LLMs in Formal Synthesis and Interpretation Tasks","created":"2024-03-27","cited_by_count":3,"area":null},{"id":"2509.18458","title":"CogniLoad: A Synthetic Natural Language Reasoning Benchmark With Tunable Length, Intrinsic Difficulty, and Distractor Density","created":"2025-09-22","cited_by_count":3,"area":"lr"},{"id":"2601.12444","title":"Large Language Model for OWL Proofs","created":"2026-01-18","cited_by_count":3,"area":"lr"},{"id":"2605.25230","title":"Boosting Inference with Guided Reasoning: Stochastic Exploration for Recursive Models","created":"2026-05-24","cited_by_count":3,"area":null},{"id":"2607.26212","title":"Multi-Agent Debate Strategies: Survey, Taxonomy, and Challenges","created":"2026-07-28","cited_by_count":3,"area":"agents"}],"next_cursor":"100"}