{"total":87,"rows":[{"id":"2210.11610","title":"Large Language Models Can Self-Improve","created":"2022-10-20","cited_by_count":664,"area":"lr"},{"id":"2204.03162","title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","created":"2022-04-07","cited_by_count":529,"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":"2304.03439","title":"Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4","created":"2023-04-07","cited_by_count":202,"area":"lr"},{"id":"2205.11822","title":"Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations","created":"2022-05-24","cited_by_count":159,"area":"lr"},{"id":"2305.12744","title":"Fact-Checking Complex Claims with Program-Guided Reasoning","created":"2023-05-22","cited_by_count":146,"area":"lr"},{"id":"2309.17249","title":"Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineering","created":"2023-09-29","cited_by_count":94,"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":"2304.10703","title":"ReCEval: Evaluating Reasoning Chains via Correctness and Informativeness","created":"2023-04-21","cited_by_count":77,"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":"2402.00559","title":"A Chain-of-Thought Is as Strong as Its Weakest Link: A Benchmark for Verifiers of Reasoning Chains","created":"2024-02-01","cited_by_count":65,"area":"lr"},{"id":"2402.05808","title":"Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning","created":"2024-02-08","cited_by_count":65,"area":"lr"},{"id":"2305.14825","title":"Large Language Models are In-Context Semantic Reasoners rather than Symbolic Reasoners","created":"2023-05-24","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":"2303.00293","title":"How Robust is GPT-3.5 to Predecessors? A Comprehensive Study on Language Understanding Tasks","created":"2023-03-01","cited_by_count":58,"area":"lr"},{"id":"2201.11473","title":"Reasoning Like Program Executors","created":"2022-01-27","cited_by_count":45,"area":"lr"},{"id":"2302.04752","title":"Benchmarks for Automated Commonsense Reasoning: A Survey","created":"2023-02-09","cited_by_count":40,"area":"lr"},{"id":"2310.00835","title":"TRAM: Benchmarking Temporal Reasoning for Large Language Models","created":"2023-10-02","cited_by_count":40,"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":"2310.18659","title":"DetermLR: Augmenting LLM-based Logical Reasoning from Indeterminacy to Determinacy","created":"2023-10-28","cited_by_count":34,"area":"lr"},{"id":"2502.09457","title":"A Survey of Multilingual Reasoning in Language Models","created":"2025-02-13","cited_by_count":33,"area":"lr"},{"id":"2403.02738","title":"Causal Prompting: Debiasing Large Language Model Prompting based on Front-Door Adjustment","created":"2024-03-05","cited_by_count":30,"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":"2303.12513","title":"Is BERT Blind? Exploring the Effect of Vision-and-Language Pretraining on Visual Language Understanding","created":"2023-03-21","cited_by_count":20,"area":"lr"},{"id":"2212.10114","title":"True Detective: A Deep Abductive Reasoning Benchmark Undoable for GPT-3 and Challenging for GPT-4","created":"2022-12-20","cited_by_count":19,"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":"2502.19587","title":"NeoBERT: A Next-Generation BERT","created":"2025-02-26","cited_by_count":16,"area":"lr"},{"id":"2305.11662","title":"Separating form and meaning: Using self-consistency to quantify task understanding across multiple senses","created":"2023-05-19","cited_by_count":15,"area":"lr"},{"id":"2402.10528","title":"Can We Verify Step by Step for Incorrect Answer Detection?","created":"2024-02-16","cited_by_count":15,"area":"lr"},{"id":"2210.08590","title":"Zero-Shot Learners for Natural Language Understanding via a Unified Multiple Choice Perspective","created":"2022-10-16","cited_by_count":14,"area":"lr"},{"id":"2210.12887","title":"Retrieval Augmentation for Commonsense Reasoning: A Unified Approach","created":"2022-10-23","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":"2302.06729","title":"STREET: A Multi-Task Structured Reasoning and Explanation Benchmark","created":"2023-02-13","cited_by_count":13,"area":"lr"},{"id":"2306.02520","title":"A Study of Situational Reasoning for Traffic Understanding","created":"2023-06-05","cited_by_count":13,"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":"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":"2303.15714","title":"Explicit Planning Helps Language Models in Logical Reasoning","created":"2023-03-28","cited_by_count":12,"area":"lr"},{"id":"2402.19467","title":"TV-TREES: Multimodal Entailment Trees for Neuro-Symbolic Video Reasoning","created":"2024-02-29","cited_by_count":12,"area":"lr"},{"id":"2305.12599","title":"Abstract Meaning Representation-Based Logic-Driven Data Augmentation for Logical Reasoning","created":"2023-05-21","cited_by_count":11,"area":"lr"},{"id":"2406.04215","title":"mCSQA: Multilingual Commonsense Reasoning Dataset with Unified Creation Strategy by Language Models and Humans","created":"2024-06-06","cited_by_count":10,"area":"lr"},{"id":"2308.01684","title":"Baby's CoThought: Leveraging Large Language Models for Enhanced Reasoning in Compact Models","created":"2023-08-03","cited_by_count":9,"area":"lr"},{"id":"2203.10557","title":"A Neural-Symbolic Approach to Natural Language Understanding","created":"2022-03-20","cited_by_count":8,"area":"lr"},{"id":"2210.11708","title":"Metric-guided Distillation: Distilling Knowledge from the Metric to Ranker and Retriever for Generative Commonsense Reasoning","created":"2022-10-21","cited_by_count":8,"area":"lr"},{"id":"2211.05417","title":"Can Transformers Reason in Fragments of Natural Language?","created":"2022-11-10","cited_by_count":8,"area":"lr"},{"id":"2405.01345","title":"The Power of Question Translation Training in Multilingual Reasoning: Broadened Scope and Deepened Insights","created":"2024-05-02","cited_by_count":7,"area":"lr"},{"id":"2202.13529","title":"KMIR: A Benchmark for Evaluating Knowledge Memorization, Identification and Reasoning Abilities of Language Models","created":"2022-02-28","cited_by_count":6,"area":"lr"},{"id":"2303.09427","title":"Logical Implications for Visual Question Answering Consistency","created":"2023-03-16","cited_by_count":6,"area":"lr"},{"id":"2305.08246","title":"Learning Non-linguistic Skills without Sacrificing Linguistic Proficiency","created":"2023-05-14","cited_by_count":5,"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":"2604.08016","title":"Wiring the 'Why': A Unified Taxonomy and Survey of Abductive Reasoning in LLMs","created":"2026-04-09","cited_by_count":5,"area":"lr"},{"id":"2306.09918","title":"No Strong Feelings One Way or Another: Re-operationalizing Neutrality in Natural Language Inference","created":"2023-06-16","cited_by_count":4,"area":"lr"},{"id":"2502.03748","title":"Rethinking Residual Distribution in Locate-then-Edit Model Editing","created":"2025-02-06","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":"2209.07760","title":"Possible Stories: Evaluating Situated Commonsense Reasoning under Multiple Possible Scenarios","created":"2022-09-16","cited_by_count":3,"area":"lr"},{"id":"2210.07519","title":"Can Language Representation Models Think in Bets?","created":"2022-10-14","cited_by_count":3,"area":"lr"},{"id":"2210.11265","title":"Disentangling Reasoning Capabilities from Language Models with Compositional Reasoning Transformers","created":"2022-10-20","cited_by_count":3,"area":"lr"},{"id":"2210.12259","title":"Enhancing Tabular Reasoning with Pattern Exploiting Training","created":"2022-10-21","cited_by_count":3,"area":"lr"},{"id":"2306.15273","title":"IDOL: Indicator-oriented Logic Pre-training for Logical Reasoning","created":"2023-06-27","cited_by_count":3,"area":"lr"},{"id":"2502.14155","title":"Giving AI Personalities Leads to More Human-Like Reasoning","created":"2025-02-19","cited_by_count":3,"area":"lr"},{"id":"2507.07439","title":"Towards Interpretable Time Series Foundation Models","created":"2025-07-10","cited_by_count":3,"area":"lr"},{"id":"2207.01450","title":"Discourse-Aware Graph Networks for Textual Logical Reasoning","created":"2022-07-04","cited_by_count":2,"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":"2212.07798","title":"Utilizing Background Knowledge for Robust Reasoning over Traffic Situations","created":"2022-12-04","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":"2306.14790","title":"Automatic Assessment of Divergent Thinking in Chinese Language with TransDis: A Transformer-Based Language Model Approach","created":"2023-06-26","cited_by_count":2,"area":"lr"},{"id":"2309.08969","title":"Rethinking STS and NLI in Large Language Models","created":"2023-09-16","cited_by_count":2,"area":"lr"},{"id":"2311.04659","title":"Pragmatic Reasoning Unlocks Quantifier Semantics for Foundation Models","created":"2023-11-08","cited_by_count":2,"area":"lr"},{"id":"2501.13397","title":"ExLM: Rethinking the Impact of [MASK] Tokens in Masked Language Models","created":"2025-01-23","cited_by_count":2,"area":"lr"},{"id":"2509.08105","title":"MERLIN: Multi-Stage Curriculum Alignment for Multilingual Encoder-LLM Integration in Cross-Lingual Reasoning","created":"2025-09-09","cited_by_count":2,"area":"lr"},{"id":"2203.00160","title":"Semantic Sentence Composition Reasoning for Multi-Hop Question Answering","created":"2022-03-01","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":"2507.15707","title":"Is Large Language Model Performance on Reasoning Tasks Impacted by Different Ways Questions Are Asked?","created":"2025-07-21","cited_by_count":1,"area":"lr"},{"id":"2607.23458","title":"Two Regimes of Chain-of-Thought Unfaithfulness: Metric-Based Detection Fails Where Models Are Wrong","created":"2026-07-26","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":"2307.11767","title":"Recognition of Mental Adjectives in An Efficient and Automatic Style","created":"2023-07-16","cited_by_count":0,"area":"lr"},{"id":"2511.03372","title":"LFC-DA: Logical Formula-Controlled Data Augmentation for Enhanced Logical Reasoning","created":"2025-11-05","cited_by_count":0,"area":"lr"},{"id":"2512.12175","title":"Rethinking Label Consistency of In-Context Learning: An Implicit Transductive Label Propagation Perspective","created":"2025-12-13","cited_by_count":0,"area":"lr"},{"id":"2512.13706","title":"Mitigating Catastrophic Forgetting in Mathematical Reasoning Finetuning through Mixed Training","created":"2025-12-05","cited_by_count":0,"area":"lr"},{"id":"2512.19728","title":"Hard Negative Sample-Augmented DPO Post-Training for Small Language Models","created":"2025-12-17","cited_by_count":0,"area":"lr"},{"id":"2602.06446","title":"CORE: Comprehensive Ontological Relation Evaluation for Large Language Models","created":"2026-02-06","cited_by_count":0,"area":"lr"},{"id":"2606.09251","title":"TruthSplit: Operationalizing Conditional Validity in Arguments Through Multi-Perspective Reasoning","created":"2026-06-08","cited_by_count":0,"area":"lr"},{"id":"2607.19678","title":"Reference-Free Evaluation of Reasoning in Open-Ended Question Answering","created":"2026-07-22","cited_by_count":0,"area":"lr"},{"id":"2608.09742","title":"Rethinking Factor Sharing in Federated LoRA: A Rank-Aware Adaptive Approach","created":"2026-08-10","cited_by_count":0,"area":"lr"},{"id":"2609.05284","title":"GUT: Quantifying and Optimizing the Reasoning Uncertainty of LLMs via Graph Complexity","created":"2026-09-04","cited_by_count":0,"area":"lr"},{"id":"2609.24831","title":"GRUET: Quantifying Uncertainty of Agentic Reasoning-and-Acting Processes","created":"2026-09-21","cited_by_count":0,"area":"lr"},{"id":"2609.36935","title":"CoEM: Empowering Long-Context Reasoning with Commit-on-Evidence Memory","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2610.07730","title":"SanSi: A Looped Typed Decision Model for System 1.5 Thinking","created":"2026-10-06","cited_by_count":0,"area":"lr"}],"next_cursor":null}