{"total":60,"rows":[{"id":"2201.08860","title":"GreaseLM: Graph REASoning Enhanced Language Models for Question Answering","created":"2022-01-21","cited_by_count":171,"area":"lr"},{"id":"2202.07206","title":"Impact of Pretraining Term Frequencies on Few-Shot Reasoning","created":"2022-02-15","cited_by_count":142,"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":"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":"2303.14725","title":"Natural Language Reasoning, A Survey","created":"2023-03-26","cited_by_count":61,"area":"lr"},{"id":"2211.01562","title":"PINTO: Faithful Language Reasoning Using Prompt-Generated Rationales","created":"2022-11-03","cited_by_count":56,"area":"lr"},{"id":"2205.05849","title":"e-CARE: a New Dataset for Exploring Explainable Causal Reasoning","created":"2022-05-12","cited_by_count":47,"area":"lr"},{"id":"2403.09972","title":"Think Twice Before Trusting: Self-Detection for Large Language Models through Comprehensive Answer Reflection","created":"2024-03-15","cited_by_count":41,"area":"lr"},{"id":"2308.03762","title":"GPT-4 Can't Reason","created":"2023-07-21","cited_by_count":40,"area":"lr"},{"id":"2506.09987","title":"A Shortcut-aware Video-QA Benchmark for Physical Understanding via Minimal Video Pairs","created":"2025-06-11","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":"2406.06196","title":"LINGOLY: A Benchmark of Olympiad-Level Linguistic Reasoning Puzzles in Low-Resource and Extinct Languages","created":"2024-06-10","cited_by_count":28,"area":"lr"},{"id":"2511.16660","title":"Cognitive Foundations for Reasoning and Their Manifestation in LLMs","created":"2025-11-20","cited_by_count":26,"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":"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":"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":"2511.02303","title":"Unlocking the Power of Multi-Agent LLM for Reasoning: From Lazy Agents to Deliberation","created":"2025-11-04","cited_by_count":11,"area":"lr"},{"id":"2505.15960","title":"Efficient PRM Training Data Synthesis via Formal Verification","created":"2025-05-21","cited_by_count":8,"area":"lr"},{"id":"2308.10585","title":"Exploring Equation as a Better Intermediate Meaning Representation for Numerical Reasoning","created":"2023-08-21","cited_by_count":7,"area":"lr"},{"id":"2310.05450","title":"Empower Nested Boolean Logic via Self-Supervised Curriculum Learning","created":"2023-10-09","cited_by_count":7,"area":"lr"},{"id":"2305.06841","title":"Think Twice: Measuring the Efficiency of Eliminating Prediction Shortcuts of Question Answering Models","created":"2023-05-11","cited_by_count":6,"area":"lr"},{"id":"2510.03415","title":"LLMs Lean on Priors, Not Programming Language Semantics","created":"2025-10-03","cited_by_count":6,"area":"lr"},{"id":"2511.00343","title":"LingGym: How Far Are LLMs from Thinking Like Field Linguists?","created":"2025-11-01","cited_by_count":6,"area":"lr"},{"id":"2404.11717","title":"How often are errors in natural language reasoning due to paraphrastic variability?","created":"2024-04-17","cited_by_count":5,"area":"lr"},{"id":"2205.10442","title":"Down and Across: Introducing Crossword-Solving as a New NLP Benchmark","created":"2022-05-20","cited_by_count":4,"area":"lr"},{"id":"2310.05442","title":"Establishing Trustworthiness: Rethinking Tasks and Model Evaluation","created":"2023-10-09","cited_by_count":4,"area":"lr"},{"id":"2601.09929","title":"Hallucination Detection and Mitigation in Large Language Models","created":"2026-01-14","cited_by_count":4,"area":"lr"},{"id":"2210.12259","title":"Enhancing Tabular Reasoning with Pattern Exploiting Training","created":"2022-10-21","cited_by_count":3,"area":"lr"},{"id":"2602.20094","title":"CausalFlip: A Benchmark for LLM Causal Judgment Beyond Semantic Matching","created":"2026-02-23","cited_by_count":3,"area":"lr"},{"id":"2210.01258","title":"Understanding Prior Bias and Choice Paralysis in Transformer-based Language Representation Models through Four Experimental Probes","created":"2022-10-03","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":"2403.03288","title":"Should We Fear Large Language Models? A Structural Analysis of the Human Reasoning System for Elucidating LLM Capabilities and Risks Through the Lens of Heidegger's Philosophy","created":"2024-03-05","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":"2510.25776","title":"StreetMath: Study of LLMs' Approximation Behaviors","created":"2025-10-27","cited_by_count":2,"area":"lr"},{"id":"2602.11675","title":"Epistemic Regret Minimization: Label-Free Causal Critique Beyond Outcome Reward","created":"2026-02-12","cited_by_count":2,"area":"lr"},{"id":"2606.04915","title":"Caliper: Probing Lexical Anchors versus Causal Structure in LLMs","created":"2026-06-03","cited_by_count":2,"area":"lr"},{"id":"2606.28574","title":"Correct codes for the wrong reasons? validating LLMs as measurement instruments for theoretical constructs","created":"2026-06-26","cited_by_count":2,"area":"lr"},{"id":"2302.08148","title":"Empirical Investigation of Neural Symbolic Reasoning Strategies","created":"2023-02-16","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":"2504.09301","title":"Continuum-Interaction-Driven Intelligence: Human-Aligned Neural Architecture via Crystallized Reasoning and Fluid Generation","created":"2025-04-12","cited_by_count":1,"area":"lr"},{"id":"2504.18376","title":"Evaluating the Scalability and Adversarial Generalization of GRPO-Trained NLI Models","created":"2025-04-25","cited_by_count":1,"area":"lr"},{"id":"2510.17868","title":"UniCode: Augmenting Evaluation for Code Reasoning","created":"2025-10-16","cited_by_count":1,"area":"lr"},{"id":"2511.20399","title":"BengaliFig: A Low-Resource Challenge for Figurative and Culturally Grounded Reasoning in Bengali","created":"2025-11-25","cited_by_count":1,"area":"lr"},{"id":"2603.29025","title":"The Model Says Walk: How Surface Heuristics Override Implicit Constraints in LLM Reasoning","created":"2026-03-30","cited_by_count":1,"area":"lr"},{"id":"2604.04825","title":"Plausibility as Commonsense Reasoning: Humans Succeed, Large Language Models Do not","created":"2026-04-06","cited_by_count":1,"area":"lr"},{"id":"2605.22870","title":"The Readout Shortcut: Positional Number Copying Dominates Arithmetic CoT Readout in Small Language Models","created":"2026-05-20","cited_by_count":1,"area":"lr"},{"id":"2608.28018","title":"Twin Worlds: Equivariance-Based Abstention for Evidence-Grounded Reasoning","created":"2026-08-28","cited_by_count":1,"area":"lr"},{"id":"2201.04467","title":"How Does Data Corruption Affect Natural Language Understanding Models? A Study on GLUE datasets","created":"2022-01-12","cited_by_count":0,"area":"lr"},{"id":"2508.17153","title":"Natural Language Satisfiability: Exploring the Problem Distribution and Evaluating Transformer-based Language Models","created":"2025-08-23","cited_by_count":0,"area":"lr"},{"id":"2510.01236","title":"GRPO++: Enhancing Dermatological Reasoning under Low Resource Settings","created":"2025-09-23","cited_by_count":0,"area":"lr"},{"id":"2511.17290","title":"Estonian WinoGrande Dataset: Comparative Analysis of LLM Performance on Human and Machine Translation","created":"2025-11-21","cited_by_count":0,"area":"lr"},{"id":"2601.11625","title":"Reasoning Stabilization Point: A Training-Time Signal for Stable Evidence and Shortcut Reliance","created":"2026-01-12","cited_by_count":0,"area":"lr"},{"id":"2606.15686","title":"Recurrent Reasoning on Symbolic Puzzles with Sequence Models","created":"2026-04-19","cited_by_count":0,"area":"lr"},{"id":"2606.27103","title":"The Riddle Riddle: Testing Flexible Reasoning in Large Language Models and Humans","created":"2026-06-25","cited_by_count":0,"area":"lr"},{"id":"2607.14349","title":"HABIB_TAZ at SemEval-2026 Task 11: Disentangling Formal Logic from Content via Synthetic Training and Multi-Objective Optimization","created":"2026-07-15","cited_by_count":0,"area":"lr"},{"id":"2608.29431","title":"Evaluating the Semantic Specificity of Representation Steering in Language Models","created":"2026-08-29","cited_by_count":0,"area":"lr"},{"id":"2609.04463","title":"Shared circuits predict whether LLMs generalize across formats in arithmetic reasoning","created":"2026-09-03","cited_by_count":0,"area":"lr"},{"id":"2609.09372","title":"What Does MMLU Actually Measure? A Psychometric Audit of Difficulty Structure in Aggregate Benchmark Scores","created":"2026-09-08","cited_by_count":0,"area":"lr"},{"id":"2609.26610","title":"Semantic Abstraction for Natural Language Inference: a Methodological Framework for Discovering and Compensating Semantic Knowledge and Reasoning Gaps in Large Language Models","created":"2026-09-22","cited_by_count":0,"area":"lr"},{"id":"2610.03329","title":"SyntaxBench: A Statistical Diagnostic Framework for Character-Level Reasoning in Large Language Models","created":"2026-10-02","cited_by_count":0,"area":"lr"}],"next_cursor":null}