{"total":93,"rows":[{"id":"2410.05229","title":"GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models","created":"2024-10-07","cited_by_count":550,"area":"lr"},{"id":"2308.05374","title":"Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment","created":"2023-08-10","cited_by_count":401,"area":null},{"id":"2210.01240","title":"Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought","created":"2022-10-03","cited_by_count":337,"area":"lr"},{"id":"2305.15771","title":"On the Planning Abilities of Large Language Models : A Critical Investigation","created":"2023-05-25","cited_by_count":312,"area":"lr"},{"id":"2401.03065","title":"CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution","created":"2024-01-05","cited_by_count":300,"area":null},{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254,"area":null},{"id":"2209.00840","title":"FOLIO: Natural Language Reasoning with First-Order Logic","created":"2022-09-02","cited_by_count":235,"area":"lr"},{"id":"2403.06963","title":"The pitfalls of next-token prediction","created":"2024-03-11","cited_by_count":160,"area":null},{"id":"2308.13067","title":"Causal Parrots: Large Language Models May Talk Causality But Are Not Causal","created":"2023-08-24","cited_by_count":150,"area":null},{"id":"2401.06805","title":"Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoning","created":"2024-01-10","cited_by_count":136,"area":"lr"},{"id":"2208.14271","title":"Faithful Reasoning Using Large Language Models","created":"2022-08-30","cited_by_count":130,"area":"lr"},{"id":"2302.06706","title":"On the Planning Abilities of Large Language Models (A Critical Investigation with a Proposed Benchmark)","created":"2023-02-13","cited_by_count":85,"area":"lr"},{"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":"2404.01869","title":"Beyond Accuracy: Evaluating the Reasoning Behavior of Large Language Models -- A Survey","created":"2024-04-02","cited_by_count":83,"area":"lr"},{"id":"2412.16075","title":"Formal Mathematical Reasoning: A New Frontier in AI","created":"2024-12-20","cited_by_count":81,"area":"lr"},{"id":"2402.08939","title":"Premise Order Matters in Reasoning with Large Language Models","created":"2024-02-14","cited_by_count":72,"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":"2212.13894","title":"LAMBADA: Backward Chaining for Automated Reasoning in Natural Language","created":"2022-12-20","cited_by_count":66,"area":"lr"},{"id":"2304.07438","title":"Tractable Control for Autoregressive Language Generation","created":"2023-04-15","cited_by_count":65,"area":null},{"id":"2401.14295","title":"Demystifying Chains, Trees, and Graphs of Thoughts","created":"2024-01-25","cited_by_count":63,"area":"lr"},{"id":"2503.22674","title":"QuestBench: Can LLMs ask the right question to acquire information in reasoning tasks?","created":"2025-03-28","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":"2306.07934","title":"BoardgameQA: A Dataset for Natural Language Reasoning with Contradictory Information","created":"2023-06-13","cited_by_count":44,"area":"lr"},{"id":"2406.17169","title":"Multi-LogiEval: Towards Evaluating Multi-Step Logical Reasoning Ability of Large Language Models","created":"2024-06-24","cited_by_count":39,"area":"lr"},{"id":"2210.00881","title":"Predicting the Future of AI with AI: High-quality link prediction in an exponentially growing knowledge network","created":"2022-09-23","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":"2502.04381","title":"Limitations of Large Language Models in Clinical Problem-Solving Arising from Inflexible Reasoning","created":"2025-02-05","cited_by_count":31,"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":"2301.06627","title":"Dissociating language and thought in large language models","created":"2023-01-16","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":"2504.15266","title":"Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction","created":"2025-04-21","cited_by_count":29,"area":null},{"id":"2411.16679","title":"Do Large Language Models Perform Latent Multi-Hop Reasoning without Exploiting Shortcuts?","created":"2024-11-25","cited_by_count":28,"area":"lr"},{"id":"2406.12158","title":"LLMs Are Prone to Fallacies in Causal Inference","created":"2024-06-18","cited_by_count":23,"area":null},{"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":"2507.07313","title":"Frontier LLMs Still Struggle with Simple Reasoning Tasks","created":"2025-07-09","cited_by_count":21,"area":"lr"},{"id":"2602.06176","title":"Large Language Model Reasoning Failures","created":"2026-02-05","cited_by_count":21,"area":"lr"},{"id":"2412.04703","title":"Transformers Struggle to Learn to Search","created":"2024-12-06","cited_by_count":19,"area":null},{"id":"2209.15093","title":"Unpacking Large Language Models with Conceptual Consistency","created":"2022-09-29","cited_by_count":18,"area":null},{"id":"2305.03353","title":"MindGames: Targeting Theory of Mind in Large Language Models with Dynamic Epistemic Modal Logic","created":"2023-05-05","cited_by_count":18,"area":null},{"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":"2410.07432","title":"Can Transformers Reason Logically? A Study in SAT Solving","created":"2024-10-09","cited_by_count":16,"area":"lr"},{"id":"2401.12947","title":"Transformer-Based Models Are Not Yet Perfect At Learning to Emulate Structural Recursion","created":"2024-01-23","cited_by_count":14,"area":null},{"id":"2407.11373","title":"Reliable Reasoning Beyond Natural Language","created":"2024-07-16","cited_by_count":14,"area":"lr"},{"id":"2504.03930","title":"Have Large Language Models Learned to Reason? A Characterization via 3-SAT Phase Transition","created":"2025-04-04","cited_by_count":14,"area":"lr"},{"id":"2402.06634","title":"SocraSynth: Multi-LLM Reasoning with Conditional Statistics","created":"2024-01-19","cited_by_count":13,"area":"lr"},{"id":"2303.15714","title":"Explicit Planning Helps Language Models in Logical Reasoning","created":"2023-03-28","cited_by_count":12,"area":"lr"},{"id":"2211.00609","title":"A Simple, Yet Effective Approach to Finding Biases in Code Generation","created":"2022-10-31","cited_by_count":8,"area":null},{"id":"2306.04031","title":"Certified Deductive Reasoning with Language Models","created":"2023-06-06","cited_by_count":8,"area":"lr"},{"id":"2410.21490","title":"Can Large Language Models Act as Symbolic Reasoners?","created":"2024-10-28","cited_by_count":8,"area":"lr"},{"id":"2306.10645","title":"Developing Effective Educational Chatbots with ChatGPT prompts: Insights from Preliminary Tests in a Case Study on Social Media Literacy (with appendix)","created":"2023-06-18","cited_by_count":6,"area":null},{"id":"2307.01540","title":"Learning to Prompt in the Classroom to Understand AI Limits: A pilot study","created":"2023-07-04","cited_by_count":6,"area":null},{"id":"2506.23908","title":"Beyond Statistical Learning: Exact Learning Is Essential for General Intelligence","created":"2025-06-30","cited_by_count":6,"area":"lr"},{"id":"2208.08241","title":"ILLUME: Rationalizing Vision-Language Models through Human Interactions","created":"2022-08-17","cited_by_count":5,"area":"mllm"},{"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":"2410.01696","title":"CreDes: Causal Reasoning Enhancement and Dual-End Searching for Solving Long-Range Reasoning Problems using LLMs","created":"2024-10-02","cited_by_count":5,"area":"lr"},{"id":"2502.10450","title":"Trustworthy AI: Safety, Bias, and Privacy -- A Survey","created":"2025-02-11","cited_by_count":5,"area":"safety"},{"id":"2506.09433","title":"Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training","created":"2025-06-11","cited_by_count":5,"area":null},{"id":"2407.00075","title":"Logicbreaks: A Framework for Understanding Subversion of Rule-based Inference","created":"2024-06-21","cited_by_count":4,"area":"safety"},{"id":"2407.17396","title":"Systematic Relational Reasoning With Epistemic Graph Neural Networks","created":"2024-07-24","cited_by_count":4,"area":null},{"id":"2305.03445","title":"LMs stand their Ground: Investigating the Effect of Embodiment in Figurative Language Interpretation by Language Models","created":"2023-05-05","cited_by_count":3,"area":null},{"id":"2501.15857","title":"Are Transformers Able to Reason by Connecting Separated Knowledge in Training Data?","created":"2025-01-27","cited_by_count":3,"area":null},{"id":"2512.20907","title":"PanoGrounder: Bridging 2D and 3D with Panoramic Scene Representations for VLM-based 3D Visual Grounding","created":"2025-12-24","cited_by_count":3,"area":null},{"id":"2304.01771","title":"Using Language Models For Knowledge Acquisition in Natural Language Reasoning Problems","created":"2023-04-04","cited_by_count":2,"area":"lr"},{"id":"2304.09276","title":"Towards a Neural Lambda Calculus: Neurosymbolic AI Applied to the Foundations of Functional Programming","created":"2023-04-18","cited_by_count":2,"area":null},{"id":"2307.13617","title":"GPT-3 Models are Few-Shot Financial Reasoners","created":"2023-07-25","cited_by_count":2,"area":"lr"},{"id":"2311.02765","title":"Rule Learning as Machine Translation using the Atomic Knowledge Bank","created":"2023-11-05","cited_by_count":2,"area":null},{"id":"2312.11720","title":"Assessing Logical Reasoning Capabilities of Encoder-Only Transformer Models","created":"2023-12-18","cited_by_count":2,"area":"lr"},{"id":"2407.04899","title":"Algorithmic Language Models with Neurally Compiled Libraries","created":"2024-07-06","cited_by_count":2,"area":null},{"id":"2410.08130","title":"Think Beyond Size: Adaptive Prompting for More Effective Reasoning","created":"2024-10-10","cited_by_count":2,"area":"lr"},{"id":"2412.14708","title":"Creation of AI-driven Smart Spaces for Enhanced Indoor Environments -- A Survey","created":"2024-12-19","cited_by_count":2,"area":null},{"id":"2508.05474","title":"Can Large Language Models Generate Effective Datasets for Emotion Recognition in Conversations?","created":"2025-08-07","cited_by_count":2,"area":null},{"id":"2509.10414","title":"Is In-Context Learning Learning?","created":"2025-09-12","cited_by_count":2,"area":null},{"id":"2210.02095","title":"ChemAlgebra: Algebraic Reasoning on Chemical Reactions","created":"2022-10-05","cited_by_count":1,"area":null},{"id":"2308.04161","title":"Current and Future Challenges in Knowledge Representation and Reasoning","created":"2023-08-08","cited_by_count":1,"area":null},{"id":"2410.12509","title":"Benchmarking Defeasible Reasoning with Large Language Models -- Initial Experiments and Future Directions","created":"2024-10-16","cited_by_count":1,"area":"lr"},{"id":"2502.05416","title":"Deep Generative Models with Hard Linear Equality Constraints","created":"2025-02-08","cited_by_count":1,"area":null},{"id":"2506.21797","title":"Why Neural Network Can Discover Symbolic Structures with Gradient-based Training: An Algebraic and Geometric Foundation for Neurosymbolic Reasoning","created":"2025-06-26","cited_by_count":1,"area":"lr"},{"id":"2508.19035","title":"Investigating Advanced Reasoning of Large Language Models via Black-Box Environment Interaction","created":"2025-08-26","cited_by_count":1,"area":"lr"},{"id":"2602.12665","title":"Evaluating Robustness of Reasoning Models on Parameterized Logical Problems","created":"2026-02-13","cited_by_count":1,"area":"lr"},{"id":"2604.21632","title":"To See the Unseen: on the Generalization Ability of Transformers in Symbolic Reasoning","created":"2026-04-23","cited_by_count":1,"area":"lr"},{"id":"2605.04330","title":"The Scaling Properties of Implicit Deductive Reasoning in Transformers","created":"2026-05-05","cited_by_count":1,"area":"lr"},{"id":"2311.08941","title":"Transformers in the Service of Description Logic-based Contexts","created":"2023-11-15","cited_by_count":0,"area":null},{"id":"2410.04347","title":"Latent Feature Mining for Predictive Model Enhancement with Large Language Models","created":"2024-10-06","cited_by_count":0,"area":null},{"id":"2502.08415","title":"FSLI: An Interpretable Formal Semantic System for One-Dimensional Ordering Inference","created":"2025-02-12","cited_by_count":0,"area":null},{"id":"2508.07466","title":"Grounding Natural Language for Multi-agent Decision-Making with Multi-agentic LLMs","created":"2025-08-10","cited_by_count":0,"area":"agents"},{"id":"2509.04470","title":"COCORELI: Enforcing Execution Preconditions for Reliable Collaborative Instruction Following","created":"2025-08-29","cited_by_count":0,"area":null},{"id":"2512.10561","title":"Causal Reasoning Favors Encoders: On The Limits of Decoder-Only Models","created":"2025-12-11","cited_by_count":0,"area":"lr"},{"id":"2602.07602","title":"Object-Oriented Transition Modeling with Inductive Logic Programming","created":"2026-02-07","cited_by_count":0,"area":null},{"id":"2603.23867","title":"Can VLMs Reason Robustly? A Neuro-Symbolic Investigation","created":"2026-03-25","cited_by_count":0,"area":"lr"},{"id":"2605.05593","title":"Causal Probing for Internal Visual Representations in Multimodal Large Language Models","created":"2026-05-07","cited_by_count":0,"area":"mllm"},{"id":"2606.03685","title":"A Close Look At World Model Recovery In Supervised Fine-Tuned LLM Planners","created":"2026-06-02","cited_by_count":0,"area":"wm"},{"id":"2608.16707","title":"Semantic Bandits: In-Context Exploration-Exploitation is Biased by Semantic Priors","created":"2026-08-17","cited_by_count":0,"area":null}],"next_cursor":null}