{"total":104,"rows":[{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459,"area":"lr"},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708,"area":"lr"},{"id":"2209.09513","title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","created":"2022-09-20","cited_by_count":1919,"area":"lr"},{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807,"area":"lr"},{"id":"2202.12837","title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?","created":"2022-02-25","cited_by_count":1434,"area":"lr"},{"id":"2210.03493","title":"Automatic Chain of Thought Prompting in Large Language Models","created":"2022-10-07","cited_by_count":688,"area":"lr"},{"id":"2210.00720","title":"Complexity-Based Prompting for Multi-Step Reasoning","created":"2022-10-03","cited_by_count":388,"area":"lr"},{"id":"2209.14610","title":"Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoning","created":"2022-09-29","cited_by_count":350,"area":"lr"},{"id":"2212.10071","title":"Large Language Models Are Reasoning Teachers","created":"2022-12-20","cited_by_count":329,"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":"2212.08061","title":"On Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning","created":"2022-12-15","cited_by_count":194,"area":"lr"},{"id":"2205.03401","title":"The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning","created":"2022-05-06","cited_by_count":169,"area":"lr"},{"id":"2305.07004","title":"Not All Languages Are Created Equal in LLMs: Improving Multilingual Capability by Cross-Lingual-Thought Prompting","created":"2023-05-11","cited_by_count":165,"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":"2310.06117","title":"Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models","created":"2023-10-09","cited_by_count":159,"area":"lr"},{"id":"2304.09797","title":"Progressive-Hint Prompting Improves Reasoning in Large Language Models","created":"2023-04-19","cited_by_count":147,"area":"lr"},{"id":"2305.06599","title":"Structured Chain-of-Thought Prompting for Code Generation","created":"2023-05-11","cited_by_count":138,"area":"lr"},{"id":"2212.10535","title":"A Survey of Deep Learning for Mathematical Reasoning","created":"2022-12-20","cited_by_count":124,"area":"lr"},{"id":"2302.12822","title":"Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Data","created":"2023-02-24","cited_by_count":119,"area":"lr"},{"id":"2410.23123","title":"On Memorization of Large Language Models in Logical Reasoning","created":"2024-10-30","cited_by_count":117,"area":"lr"},{"id":"2503.15850","title":"Uncertainty Quantification and Confidence Calibration in Large Language Models: A Survey","created":"2025-03-20","cited_by_count":95,"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":"2210.05359","title":"Mind's Eye: Grounded Language Model Reasoning through Simulation","created":"2022-10-11","cited_by_count":84,"area":"lr"},{"id":"2203.08410","title":"Thinking about GPT-3 In-Context Learning for Biomedical IE? Think Again","created":"2022-03-16","cited_by_count":83,"area":"lr"},{"id":"2307.09476","title":"Overthinking the Truth: Understanding how Language Models Process False Demonstrations","created":"2023-07-18","cited_by_count":81,"area":"lr"},{"id":"2306.06427","title":"Boosting Language Models Reasoning with Chain-of-Knowledge Prompting","created":"2023-06-10","cited_by_count":77,"area":"lr"},{"id":"2212.09095","title":"Rethinking the Role of Scale for In-Context Learning: An Interpretability-based Case Study at 66 Billion Scale","created":"2022-12-18","cited_by_count":64,"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":"2303.08119","title":"How Many Demonstrations Do You Need for In-context Learning?","created":"2023-03-14","cited_by_count":52,"area":"lr"},{"id":"2305.04835","title":"How Do In-Context Examples Affect Compositional Generalization?","created":"2023-05-08","cited_by_count":51,"area":"lr"},{"id":"2412.14959","title":"Understanding the Dark Side of LLMs' Intrinsic Self-Correction","created":"2024-12-19","cited_by_count":42,"area":"lr"},{"id":"2304.05970","title":"Boosted Prompt Ensembles for Large Language Models","created":"2023-04-12","cited_by_count":36,"area":"lr"},{"id":"2305.14333","title":"Automatic Model Selection with Large Language Models for Reasoning","created":"2023-05-23","cited_by_count":35,"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":"2301.00355","title":"Second Thoughts are Best: Learning to Re-Align With Human Values from Text Edits","created":"2023-01-01","cited_by_count":27,"area":"lr"},{"id":"2402.06529","title":"Introspective Planning: Aligning Robots' Uncertainty with Inherent Task Ambiguity","created":"2024-02-09","cited_by_count":27,"area":"lr"},{"id":"2502.00330","title":"From Few to Many: Self-Improving Many-Shot Reasoners Through Iterative Optimization and Generation","created":"2025-02-01","cited_by_count":21,"area":"lr"},{"id":"2312.01714","title":"Retrieval-augmented Multi-modal Chain-of-Thoughts Reasoning for Large Language Models","created":"2023-12-04","cited_by_count":18,"area":"lr"},{"id":"2402.05889","title":"CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion","created":"2024-02-08","cited_by_count":17,"area":"lr"},{"id":"2304.11657","title":"Enhancing Chain-of-Thoughts Prompting with Iterative Bootstrapping in Large Language Models","created":"2023-04-23","cited_by_count":16,"area":"lr"},{"id":"2310.14607","title":"Confronting LLMs with Traditional ML: Rethinking the Fairness of Large Language Models in Tabular Classifications","created":"2023-10-23","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":"2310.05861","title":"Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Models","created":"2023-10-09","cited_by_count":14,"area":"lr"},{"id":"2401.01974","title":"Towards Truly Zero-shot Compositional Visual Reasoning with LLMs as Programmers","created":"2024-01-03","cited_by_count":14,"area":"lr"},{"id":"2402.11900","title":"Investigating Multi-Hop Factual Shortcuts in Knowledge Editing of Large Language Models","created":"2024-02-19","cited_by_count":14,"area":"lr"},{"id":"2310.13332","title":"Democratizing Reasoning Ability: Tailored Learning from Large Language Model","created":"2023-10-20","cited_by_count":13,"area":"lr"},{"id":"2412.09722","title":"GReaTer: Gradients over Reasoning Makes Smaller Language Models Strong Prompt Optimizers","created":"2024-12-12","cited_by_count":12,"area":"lr"},{"id":"2306.03799","title":"Prompt Space Optimizing Few-shot Reasoning Success with Large Language Models","created":"2023-06-06","cited_by_count":11,"area":"lr"},{"id":"2504.02111","title":"Exploring LLM Reasoning Through Controlled Prompt Variations","created":"2025-04-02","cited_by_count":10,"area":"lr"},{"id":"2609.31142","title":"JevAdvBench: A Benchmark and Black-Box Attacks for Reinforcement Learning for Calibrated Decisions Models","created":"2026-09-25","cited_by_count":10,"area":"lr"},{"id":"2310.01991","title":"Fill in the Blank: Exploring and Enhancing LLM Capabilities for Backward Reasoning in Math Word Problems","created":"2023-10-03","cited_by_count":9,"area":"lr"},{"id":"2505.14412","title":"PRL: Prompts from Reinforcement Learning","created":"2025-05-20","cited_by_count":9,"area":"lr"},{"id":"2310.15575","title":"POE: Process of Elimination for Multiple Choice Reasoning","created":"2023-10-24","cited_by_count":8,"area":"lr"},{"id":"2412.03966","title":"Demonstration Selection for In-Context Learning via Reinforcement Learning","created":"2024-12-05","cited_by_count":8,"area":"lr"},{"id":"2310.04743","title":"Resprompt: Residual Connection Prompting Advances Multi-Step Reasoning in Large Language Models","created":"2023-10-07","cited_by_count":7,"area":"lr"},{"id":"2210.05901","title":"Zero-Shot Prompting for Implicit Intent Prediction and Recommendation with Commonsense Reasoning","created":"2022-10-12","cited_by_count":6,"area":"lr"},{"id":"2310.10698","title":"Bridging Code Semantic and LLMs: Semantic Chain-of-Thought Prompting for Code Generation","created":"2023-10-16","cited_by_count":6,"area":"lr"},{"id":"2404.17809","title":"Recall, Retrieve and Reason: Towards Better In-Context Relation Extraction","created":"2024-04-27","cited_by_count":6,"area":"lr"},{"id":"2412.02906","title":"Does Few-Shot Learning Help LLM Performance in Code Synthesis?","created":"2024-12-03","cited_by_count":6,"area":"lr"},{"id":"2503.02670","title":"Multidimensional Consistency Improves Reasoning in Language Models","created":"2025-03-04","cited_by_count":6,"area":"lr"},{"id":"2604.25444","title":"One Refiner to Unlock Them All: Inference-Time Reasoning Elicitation via Reinforcement Query Refinement","created":"2026-04-28","cited_by_count":6,"area":"lr"},{"id":"2411.03877","title":"EXPLORA: Efficient Exemplar Subset Selection for Complex Reasoning","created":"2024-11-06","cited_by_count":5,"area":"lr"},{"id":"2412.07148","title":"MM-PoE: Multiple Choice Reasoning via. Process of Elimination using Multi-Modal Models","created":"2024-12-10","cited_by_count":5,"area":"lr"},{"id":"2604.06699","title":"Adaptive Prompt Structure Factorization: A Framework for Self-Discovering and Optimizing Compositional Prompt Programs","created":"2026-04-08","cited_by_count":5,"area":"lr"},{"id":"2501.10688","title":"Neural Algorithmic Reasoning for Hypergraphs with Looped Transformers","created":"2025-01-18","cited_by_count":4,"area":"lr"},{"id":"2510.04141","title":"The Artificial Intelligence Cognitive Examination: A Survey on the Evolution of Multimodal Evaluation from Recognition to Reasoning","created":"2025-10-05","cited_by_count":4,"area":"lr"},{"id":"2510.08044","title":"Towards Reliable LLM-based Robot Planning via Combined Uncertainty Estimation","created":"2025-10-09","cited_by_count":4,"area":"lr"},{"id":"2603.20640","title":"Hear Both Sides: Efficient Multi-Agent Debate via Diversity-Aware Message Retention","created":"2026-03-21","cited_by_count":4,"area":"lr"},{"id":"2210.07519","title":"Can Language Representation Models Think in Bets?","created":"2022-10-14","cited_by_count":3,"area":"lr"},{"id":"2509.06806","title":"MachineLearningLM: Scaling Many-shot In-context Learning via Continued Pretraining","created":"2025-09-08","cited_by_count":3,"area":"lr"},{"id":"2601.17376","title":"Diversified Scaling Inference in Time Series Foundation Models","created":"2026-01-24","cited_by_count":3,"area":"lr"},{"id":"2603.13173","title":"Semantic Invariance in Agentic AI","created":"2026-03-13","cited_by_count":3,"area":"lr"},{"id":"2311.13538","title":"AlignedCoT: Prompting Large Language Models via Native-Speaking Demonstrations","created":"2023-11-22","cited_by_count":2,"area":"lr"},{"id":"2507.09931","title":"Mechanistic Interpretability of LoRA-Adapted Language Models for Nuclear Reactor Safety Applications","created":"2025-07-14","cited_by_count":2,"area":"lr"},{"id":"2508.04748","title":"AttriLens-Mol: Attribute Guided Reinforcement Learning for Molecular Property Prediction with Large Language Models","created":"2025-08-06","cited_by_count":2,"area":"lr"},{"id":"2509.02093","title":"Better by Comparison: Retrieval-Augmented Contrastive Reasoning for Automatic Prompt Optimization","created":"2025-09-02","cited_by_count":2,"area":"lr"},{"id":"2601.03018","title":"Dementia-R1: Reinforced Pretraining and Reasoning from Unstructured Clinical Notes for Real-World Dementia Prognosis","created":"2026-01-06","cited_by_count":2,"area":"lr"},{"id":"2604.23333","title":"Process Supervision of Confidence Margin for Calibrated LLM Reasoning","created":"2026-04-25","cited_by_count":2,"area":"lr"},{"id":"2605.06723","title":"When Does a Language Model Commit? A Finite-Answer Theory of Pre-Verbalization Commitment","created":"2026-05-07","cited_by_count":2,"area":"lr"},{"id":"2309.15074","title":"Natural Language based Context Modeling and Reasoning for Ubiquitous Computing with Large Language Models: A Tutorial","created":"2023-09-24","cited_by_count":1,"area":"lr"},{"id":"2501.02825","title":"Randomly Sampled Language Reasoning Problems Elucidate Limitations of In-Context Learning","created":"2025-01-06","cited_by_count":1,"area":"lr"},{"id":"2604.05383","title":"Towards Effective In-context Cross-domain Knowledge Transfer via Domain-invariant-neurons-based Retrieval","created":"2026-04-07","cited_by_count":1,"area":"lr"},{"id":"2605.11599","title":"Targeted Tests for LLM Reasoning: An Audit-Constrained Protocol","created":"2026-05-12","cited_by_count":1,"area":"lr"},{"id":"2605.29170","title":"UA-Legal-Bench: A Benchmark for Evaluating Large Language Models on Ukrainian Legal Reasoning","created":"2026-05-27","cited_by_count":1,"area":"lr"},{"id":"2305.16048","title":"UFO: Unified Fact Obtaining for Commonsense Question Answering","created":"2023-05-25","cited_by_count":0,"area":"lr"},{"id":"2408.13028","title":"In-Context Learning with Reinforcement Learning for Incomplete Utterance Rewriting","created":"2024-08-23","cited_by_count":0,"area":"lr"},{"id":"2412.08090","title":"Multilingual LLMs Inherently Reward In-Language Time-Sensitive Semantic Alignment for Low-Resource Languages","created":"2024-12-11","cited_by_count":0,"area":"lr"},{"id":"2510.05133","title":"Characterizing Model Behavior Under Synthetic Data Training: An Empirical Study Across Scales and Mixing Ratios","created":"2025-10-01","cited_by_count":0,"area":"lr"},{"id":"2510.16302","title":"DTKG: Dual-Track Knowledge Graph-Verified Reasoning Framework for Multi-Hop QA","created":"2025-10-18","cited_by_count":0,"area":"lr"},{"id":"2511.04053","title":"Interpreting Multi-Attribute Confounding through Numerical Attributes in Large Language Models","created":"2025-11-06","cited_by_count":0,"area":"lr"},{"id":"2512.19247","title":"Auto-Prompting with Retrieval Guidance for Frame Detection in Logistics","created":"2025-12-22","cited_by_count":0,"area":"lr"},{"id":"2603.20170","title":"Learning Dynamic Belief Graphs for Theory-of-mind Reasoning","created":"2026-03-20","cited_by_count":0,"area":"lr"},{"id":"2604.01113","title":"CARE: Privacy-Compliant Agentic Reasoning with Evidence Discordance","created":"2026-04-01","cited_by_count":0,"area":"lr"},{"id":"2604.10034","title":"AI Achieves a Perfect LSAT Score","created":"2026-04-11","cited_by_count":0,"area":"lr"},{"id":"2604.11133","title":"How Robust Are Large Language Models for Clinical Numeracy? An Empirical Study on Numerical Reasoning Abilities in Clinical Contexts","created":"2026-04-13","cited_by_count":0,"area":"lr"},{"id":"2604.19488","title":"CoDA: Towards Effective Cross-domain Knowledge Transfer via CoT-guided Domain Adaptation","created":"2026-04-21","cited_by_count":0,"area":"lr"},{"id":"2604.27540","title":"In-Context Examples Suppress Scientific Knowledge Recall in LLMs","created":"2026-04-30","cited_by_count":0,"area":"lr"},{"id":"2606.13591","title":"Confidence Composition for Multiagent Language Model Systems","created":"2026-06-11","cited_by_count":0,"area":"lr"},{"id":"2608.01175","title":"The Graph Language: How Knowledge Graphs Speak to Large Language Models","created":"2026-08-02","cited_by_count":0,"area":"lr"},{"id":"2608.05166","title":"Conditional Cognitive Biases in LLMs: How Biased User Turns Modulate In-Context Reasoning","created":"2026-05-26","cited_by_count":0,"area":"lr"}],"next_cursor":"100"}