{"total":71,"rows":[{"id":"2305.04388","title":"Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting","created":"2023-05-07","cited_by_count":1122,"area":"lr"},{"id":"2212.10403","title":"Towards Reasoning in Large Language Models: A Survey","created":"2022-12-20","cited_by_count":596,"area":"lr"},{"id":"2302.07842","title":"Augmented Language Models: a Survey","created":"2023-02-15","cited_by_count":403,"area":"lr"},{"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":"2212.10071","title":"Large Language Models Are Reasoning Teachers","created":"2022-12-20","cited_by_count":329,"area":"lr"},{"id":"2307.02477","title":"Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks","created":"2023-07-05","cited_by_count":246,"area":"lr"},{"id":"2212.09196","title":"Emergent Analogical Reasoning in Large Language Models","created":"2022-12-19","cited_by_count":240,"area":"lr"},{"id":"2308.03188","title":"Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies","created":"2023-08-06","cited_by_count":238,"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":"2306.15448","title":"Understanding Social Reasoning in Language Models with Language Models","created":"2023-06-21","cited_by_count":172,"area":"lr"},{"id":"2402.14848","title":"Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models","created":"2024-02-19","cited_by_count":152,"area":"lr"},{"id":"2305.14536","title":"MathDial: A Dialogue Tutoring Dataset with Rich Pedagogical Properties Grounded in Math Reasoning Problems","created":"2023-05-23","cited_by_count":131,"area":"lr"},{"id":"2208.14271","title":"Faithful Reasoning Using Large Language Models","created":"2022-08-30","cited_by_count":130,"area":"lr"},{"id":"2309.05660","title":"Hypothesis Search: Inductive Reasoning with Language Models","created":"2023-09-11","cited_by_count":120,"area":"lr"},{"id":"2310.08559","title":"Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement","created":"2023-10-12","cited_by_count":89,"area":"lr"},{"id":"2210.05359","title":"Mind's Eye: Grounded Language Model Reasoning through Simulation","created":"2022-10-11","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":"2504.00050","title":"JudgeLRM: Large Reasoning Models as a Judge","created":"2025-03-31","cited_by_count":78,"area":"lr"},{"id":"2406.11050","title":"A Peek into Token Bias: Large Language Models Are Not Yet Genuine Reasoners","created":"2024-06-16","cited_by_count":73,"area":"lr"},{"id":"2306.03917","title":"Turning large language models into cognitive models","created":"2023-06-06","cited_by_count":67,"area":"lr"},{"id":"2303.14725","title":"Natural Language Reasoning, A Survey","created":"2023-03-26","cited_by_count":61,"area":"lr"},{"id":"2411.01855","title":"Can Language Models Learn to Skip Steps?","created":"2024-11-04","cited_by_count":59,"area":"lr"},{"id":"2408.08862","title":"Visual Agents as Fast and Slow Thinkers","created":"2024-08-16","cited_by_count":53,"area":"lr"},{"id":"2506.21215","title":"Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?","created":"2025-06-26","cited_by_count":38,"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":"2304.07919","title":"Chain of Thought Prompt Tuning in Vision Language Models","created":"2023-04-16","cited_by_count":34,"area":"lr"},{"id":"2502.20332","title":"Emergent Symbolic Mechanisms Support Abstract Reasoning in Large Language Models","created":"2025-02-27","cited_by_count":31,"area":"lr"},{"id":"2403.13312","title":"LeanReasoner: Boosting Complex Logical Reasoning with Lean","created":"2024-03-20","cited_by_count":28,"area":"lr"},{"id":"2412.08819","title":"HARP: A challenging human-annotated math reasoning benchmark","created":"2024-12-11","cited_by_count":27,"area":"lr"},{"id":"2402.06025","title":"Doing Experiments and Revising Rules with Natural Language and Probabilistic Reasoning","created":"2024-02-08","cited_by_count":24,"area":"lr"},{"id":"2402.09193","title":"(Ir)rationality and Cognitive Biases in Large Language Models","created":"2024-02-14","cited_by_count":23,"area":"lr"},{"id":"2406.02787","title":"Disentangling Logic: The Role of Context in Large Language Model Reasoning Capabilities","created":"2024-06-04","cited_by_count":22,"area":"lr"},{"id":"2311.00445","title":"A Systematic Comparison of Syllogistic Reasoning in Humans and Language Models","created":"2023-11-01","cited_by_count":20,"area":"lr"},{"id":"2401.09395","title":"Evaluating LLMs' Mathematical and Coding Competency through Ontology-guided Interventions","created":"2024-01-17","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":"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":"2306.12567","title":"Evaluating Large Language Models with NeuBAROCO: Syllogistic Reasoning Ability and Human-like Biases","created":"2023-06-21","cited_by_count":14,"area":"lr"},{"id":"2408.04403","title":"Exploring Reasoning Biases in Large Language Models Through Syllogism: Insights from the NeuBAROCO Dataset","created":"2024-08-08","cited_by_count":14,"area":"lr"},{"id":"2402.14856","title":"Comparing Inferential Strategies of Humans and Large Language Models in Deductive Reasoning","created":"2024-02-20","cited_by_count":13,"area":"lr"},{"id":"2406.11341","title":"A Systematic Analysis of Large Language Models as Soft Reasoners: The Case of Syllogistic Inferences","created":"2024-06-17","cited_by_count":13,"area":"lr"},{"id":"2505.20223","title":"Chain-of-Thought for Autonomous Driving: A Comprehensive Survey and Future Prospects","created":"2025-05-26","cited_by_count":12,"area":"lr"},{"id":"2410.08126","title":"Mars: Situated Inductive Reasoning in an Open-World Environment","created":"2024-10-10","cited_by_count":11,"area":"lr"},{"id":"2401.17169","title":"Conditional and Modal Reasoning in Large Language Models","created":"2024-01-30","cited_by_count":9,"area":"lr"},{"id":"2410.14399","title":"SylloBio-NLI: Evaluating Large Language Models on Biomedical Syllogistic Reasoning","created":"2024-10-18","cited_by_count":9,"area":"lr"},{"id":"2604.02485","title":"Failing to Falsify: Evaluating and Mitigating Confirmation Bias in Language Models","created":"2026-04-02","cited_by_count":9,"area":"lr"},{"id":"2306.04031","title":"Certified Deductive Reasoning with Language Models","created":"2023-06-06","cited_by_count":8,"area":"lr"},{"id":"2406.00284","title":"A Closer Look at Logical Reasoning with LLMs: The Choice of Tool Matters","created":"2024-06-01","cited_by_count":8,"area":"lr"},{"id":"2212.08607","title":"MURMUR: Modular Multi-Step Reasoning for Semi-Structured Data-to-Text Generation","created":"2022-12-16","cited_by_count":7,"area":"lr"},{"id":"2504.04110","title":"PEIRCE: Unifying Material and Formal Reasoning via LLM-Driven Neuro-Symbolic Refinement","created":"2025-04-05","cited_by_count":7,"area":"lr"},{"id":"2505.09614","title":"Language Agents Mirror Human Causal Reasoning Biases. How Can We Help Them Think Like Scientists?","created":"2025-05-14","cited_by_count":7,"area":"lr"},{"id":"2402.14404","title":"On the Tip of the Tongue: Analyzing Conceptual Representation in Large Language Models with Reverse-Dictionary Probe","created":"2024-02-22","cited_by_count":6,"area":"lr"},{"id":"2502.12896","title":"None of the Others: a General Technique to Distinguish Reasoning from Memorization in Multiple-Choice LLM Evaluation Benchmarks","created":"2025-02-18","cited_by_count":6,"area":"lr"},{"id":"2307.01784","title":"The Inner Sentiments of a Thought","created":"2023-07-04","cited_by_count":4,"area":"lr"},{"id":"2505.09396","title":"The Influence of Human-inspired Agentic Sophistication in LLM-driven Strategic Reasoners","created":"2025-05-14","cited_by_count":3,"area":"lr"},{"id":"2505.22318","title":"Flying Pigs, FaR and Beyond: Evaluating LLM Reasoning in Counterfactual Worlds","created":"2025-05-28","cited_by_count":3,"area":"lr"},{"id":"2602.02462","title":"Abstract Activation Spaces for Content-Invariant Reasoning in Large Language Models","created":"2026-02-02","cited_by_count":3,"area":"lr"},{"id":"2312.11720","title":"Assessing Logical Reasoning Capabilities of Encoder-Only Transformer Models","created":"2023-12-18","cited_by_count":2,"area":"lr"},{"id":"2406.18762","title":"Categorical Syllogisms Revisited: A Review of the Logical Reasoning Abilities of LLMs for Analyzing Categorical Syllogism","created":"2024-06-26","cited_by_count":2,"area":"lr"},{"id":"2501.13833","title":"On the Reasoning Capacity of AI Models and How to Quantify It","created":"2025-01-23","cited_by_count":2,"area":"lr"},{"id":"2506.06955","title":"BIS Reasoning 1.0: The First Large-Scale Japanese Benchmark for Belief-Inconsistent Syllogistic Reasoning","created":"2025-06-08","cited_by_count":2,"area":"lr"},{"id":"2510.25860","title":"Through the Judge's Eyes: Inferred Thinking Traces Improve Reliability of LLM Raters","created":"2025-10-29","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":"2312.07527","title":"BaRDa: A Belief and Reasoning Dataset that Separates Factual Accuracy and Reasoning Ability","created":"2023-12-12","cited_by_count":1,"area":"lr"},{"id":"2406.02804","title":"ACCORD: Closing the Commonsense Measurability Gap","created":"2024-06-04","cited_by_count":1,"area":"lr"},{"id":"2407.20244","title":"Steamroller Problems: An Evaluation of LLM Reasoning Capability with Automated Theorem Prover Strategies","created":"2024-07-17","cited_by_count":1,"area":"lr"},{"id":"2509.24351","title":"From Static to Dynamic: Adaptive Monte Carlo Search for Mathematical Process Supervision","created":"2025-09-29","cited_by_count":1,"area":"lr"},{"id":"2506.21580","title":"From General Reasoning to Domain Expertise: Uncovering the Limits of Generalization in Large Language Models","created":"2025-06-16","cited_by_count":0,"area":"lr"},{"id":"2603.01580","title":"Markovian ODE-guided scoring can assess the quality of offline reasoning traces in language models","created":"2026-03-02","cited_by_count":0,"area":"lr"},{"id":"2607.14561","title":"MARS: Multi-hop Adaptive Retrieval and SPARQL Generation for KGQA","created":"2026-07-16","cited_by_count":0,"area":"lr"},{"id":"2608.08514","title":"Reproducing and Stress-Testing Two Approaches to LLM Reasoning Reliability: Test-Time Probability Aggregation and Logic-Representation Editing","created":"2026-08-09","cited_by_count":0,"area":"lr"},{"id":"2608.12374","title":"Are you Talking Logic to Me? Assessing Language Models Syllogistic Reasoning Capabilities","created":"2026-07-22","cited_by_count":0,"area":"lr"}],"next_cursor":null}