{"total":152,"rows":[{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576,"area":null},{"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":"2211.14275","title":"Solving math word problems with process- and outcome-based feedback","created":"2022-11-25","cited_by_count":901,"area":"lr"},{"id":"2302.04023","title":"A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity","created":"2023-02-08","cited_by_count":894,"area":"lr"},{"id":"2205.09712","title":"Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning","created":"2022-05-19","cited_by_count":334,"area":"lr"},{"id":"2203.07540","title":"ScienceWorld: Is your Agent Smarter than a 5th Grader?","created":"2022-03-14","cited_by_count":327,"area":"lr"},{"id":"2212.09597","title":"Reasoning with Language Model Prompting: A Survey","created":"2022-12-19","cited_by_count":252,"area":"lr"},{"id":"2212.07919","title":"ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoning","created":"2022-12-15","cited_by_count":177,"area":"lr"},{"id":"2208.14271","title":"Faithful Reasoning Using Large Language Models","created":"2022-08-30","cited_by_count":130,"area":"lr"},{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130,"area":null},{"id":"2312.12241","title":"GeomVerse: A Systematic Evaluation of Large Models for Geometric Reasoning","created":"2023-12-19","cited_by_count":108,"area":"lr"},{"id":"2210.03050","title":"State-of-the-art generalisation research in NLP: A taxonomy and review","created":"2022-10-06","cited_by_count":98,"area":null},{"id":"2305.11595","title":"Examining Inter-Consistency of Large Language Models Collaboration: An In-depth Analysis via Debate","created":"2023-05-19","cited_by_count":97,"area":null},{"id":"2308.04592","title":"Shepherd: A Critic for Language Model Generation","created":"2023-08-08","cited_by_count":97,"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":"2205.12910","title":"NaturalProver: Grounded Mathematical Proof Generation with Language Models","created":"2022-05-25","cited_by_count":72,"area":null},{"id":"2503.03750","title":"The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systems","created":"2025-03-05","cited_by_count":72,"area":"agents"},{"id":"2404.05221","title":"LLM Reasoners: New Evaluation, Library, and Analysis of Step-by-Step Reasoning with Large Language Models","created":"2024-04-08","cited_by_count":70,"area":"wm"},{"id":"2212.13894","title":"LAMBADA: Backward Chaining for Automated Reasoning in Natural Language","created":"2022-12-20","cited_by_count":66,"area":"lr"},{"id":"2306.09841","title":"Are Large Language Models Really Good Logical Reasoners? A Comprehensive Evaluation and Beyond","created":"2023-06-16","cited_by_count":65,"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":"2401.14295","title":"Demystifying Chains, Trees, and Graphs of Thoughts","created":"2024-01-25","cited_by_count":63,"area":"lr"},{"id":"2502.12289","title":"Evaluating Step-by-step Reasoning Traces: A Survey","created":"2025-02-17","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":"2305.03453","title":"T-SciQ: Teaching Multimodal Chain-of-Thought Reasoning via Mixed Large Language Model Signals for Science Question Answering","created":"2023-05-05","cited_by_count":60,"area":"lr"},{"id":"2404.09939","title":"A Survey on Deep Learning for Theorem Proving","created":"2024-04-15","cited_by_count":57,"area":null},{"id":"2205.12443","title":"Generating Natural Language Proofs with Verifier-Guided Search","created":"2022-05-25","cited_by_count":52,"area":null},{"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":"2210.12217","title":"Entailer: Answering Questions with Faithful and Truthful Chains of Reasoning","created":"2022-10-21","cited_by_count":38,"area":null},{"id":"2204.13074","title":"Towards Teachable Reasoning Systems: Using a Dynamic Memory of User Feedback for Continual System Improvement","created":"2022-04-27","cited_by_count":37,"area":"lr"},{"id":"2201.06028","title":"Natural Language Deduction through Search over Statement Compositions","created":"2022-01-16","cited_by_count":35,"area":null},{"id":"2305.12477","title":"GPT-3.5, GPT-4, or BARD? Evaluating LLMs Reasoning Ability in Zero-Shot Setting and Performance Boosting Through Prompts","created":"2023-05-21","cited_by_count":34,"area":"lr"},{"id":"2402.13610","title":"Data-driven Discovery with Large Generative Models","created":"2024-02-21","cited_by_count":34,"area":null},{"id":"2212.09146","title":"Can Retriever-Augmented Language Models Reason? The Blame Game Between the Retriever and the Language Model","created":"2022-12-18","cited_by_count":32,"area":"lr"},{"id":"2406.00936","title":"A Survey of Useful LLM Evaluation","created":"2024-06-03","cited_by_count":29,"area":null},{"id":"2408.00114","title":"Inductive or Deductive? Rethinking the Fundamental Reasoning Abilities of LLMs","created":"2024-07-31","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":"2104.08825","title":"Flexible Generation of Natural Language Deductions","created":"2021-04-18","cited_by_count":28,"area":null},{"id":"2310.00074","title":"SocREval: Large Language Models with the Socratic Method for Reference-Free Reasoning Evaluation","created":"2023-09-29","cited_by_count":27,"area":"lr"},{"id":"2205.09224","title":"Entailment Tree Explanations via Iterative Retrieval-Generation Reasoner","created":"2022-05-18","cited_by_count":26,"area":"lr"},{"id":"2301.11596","title":"ThoughtSource: A central hub for large language model reasoning data","created":"2023-01-27","cited_by_count":23,"area":"lr"},{"id":"2402.17630","title":"Fine-Grained Natural Language Inference Based Faithfulness Evaluation for Diverse Summarisation Tasks","created":"2024-02-27","cited_by_count":23,"area":null},{"id":"2410.03136","title":"Deliberate Reasoning in Language Models as Structure-Aware Planning with an Accurate World Model","created":"2024-10-04","cited_by_count":23,"area":"wm"},{"id":"2210.12152","title":"WikiWhy: Answering and Explaining Cause-and-Effect Questions","created":"2022-10-21","cited_by_count":21,"area":null},{"id":"2406.06950","title":"A Probabilistic Framework for LLM Hallucination Detection via Belief Tree Propagation","created":"2024-06-11","cited_by_count":21,"area":null},{"id":"2210.02498","title":"Honest Students from Untrusted Teachers: Learning an Interpretable Question-Answering Pipeline from a Pretrained Language Model","created":"2022-10-05","cited_by_count":20,"area":null},{"id":"2405.03146","title":"Quantifying the Capabilities of LLMs across Scale and Precision","created":"2024-05-06","cited_by_count":19,"area":null},{"id":"2305.06349","title":"RECKONING: Reasoning through Dynamic Knowledge Encoding","created":"2023-05-10","cited_by_count":18,"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":"2107.04132","title":"A Systematic Survey of Text Worlds as Embodied Natural Language Environments","created":"2021-07-08","cited_by_count":17,"area":null},{"id":"2205.02593","title":"METGEN: A Module-Based Entailment Tree Generation Framework for Answer Explanation","created":"2022-05-05","cited_by_count":17,"area":"lr"},{"id":"2311.09174","title":"AbsPyramid: Benchmarking the Abstraction Ability of Language Models with a Unified Entailment Graph","created":"2023-11-15","cited_by_count":17,"area":null},{"id":"2209.07662","title":"NELLIE: A Neuro-Symbolic Inference Engine for Grounded, Compositional, and Explainable Reasoning","created":"2022-09-16","cited_by_count":16,"area":"lr"},{"id":"2305.02556","title":"Faithful Question Answering with Monte-Carlo Planning","created":"2023-05-04","cited_by_count":16,"area":"lr"},{"id":"2204.07190","title":"Measuring Compositional Consistency for Video Question Answering","created":"2022-04-14","cited_by_count":15,"area":null},{"id":"2305.14250","title":"Language Models with Rationality","created":"2023-05-23","cited_by_count":15,"area":null},{"id":"2109.10604","title":"NOAHQA: Numerical Reasoning with Interpretable Graph Question Answering Dataset","created":"2021-09-22","cited_by_count":14,"area":null},{"id":"2209.10492","title":"Summarization Programs: Interpretable Abstractive Summarization with Neural Modular Trees","created":"2022-09-21","cited_by_count":14,"area":null},{"id":"2209.12613","title":"Factual and Informative Review Generation for Explainable Recommendation","created":"2022-09-12","cited_by_count":14,"area":null},{"id":"2402.13415","title":"Structure Guided Prompt: Instructing Large Language Model in Multi-Step Reasoning by Exploring Graph Structure of the Text","created":"2024-02-20","cited_by_count":14,"area":"lr"},{"id":"2409.12929","title":"LogicPro: Improving Complex Logical Reasoning via Program-Guided Learning","created":"2024-09-19","cited_by_count":14,"area":"lr"},{"id":"2504.01001","title":"Zero-shot Benchmarking: A Framework for Flexible and Scalable Automatic Evaluation of Language Models","created":"2025-04-01","cited_by_count":14,"area":null},{"id":"2212.06295","title":"Despite \"super-human\" performance, current LLMs are unsuited for decisions about ethics and safety","created":"2022-12-13","cited_by_count":13,"area":null},{"id":"2302.06729","title":"STREET: A Multi-Task Structured Reasoning and Explanation Benchmark","created":"2023-02-13","cited_by_count":13,"area":"lr"},{"id":"2310.12426","title":"MAF: Multi-Aspect Feedback for Improving Reasoning in Large Language Models","created":"2023-10-19","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":"2203.15099","title":"LogicInference: A New Dataset for Teaching Logical Inference to seq2seq Models","created":"2022-03-28","cited_by_count":12,"area":null},{"id":"2211.00614","title":"Natural Language Deduction with Incomplete Information","created":"2022-11-01","cited_by_count":12,"area":null},{"id":"2402.14798","title":"Enhancing Systematic Decompositional Natural Language Inference Using Informal Logic","created":"2024-02-22","cited_by_count":12,"area":null},{"id":"2501.05069","title":"Commonsense Video Question Answering through Video-Grounded Entailment Tree Reasoning","created":"2025-01-09","cited_by_count":12,"area":"lr"},{"id":"2502.11176","title":"LogiDynamics: Unraveling the Dynamics of Inductive, Abductive and Deductive Logical Inferences in LLM Reasoning","created":"2025-02-16","cited_by_count":12,"area":"lr"},{"id":"2511.04662","title":"VeriCoT: Neuro-symbolic Chain-of-Thought Validation via Logical Consistency Checks","created":"2025-11-06","cited_by_count":11,"area":"lr"},{"id":"2408.10918","title":"CHECKWHY: Causal Fact Verification via Argument Structure","created":"2024-08-20","cited_by_count":9,"area":"lr"},{"id":"2505.01595","title":"Always Tell Me The Odds: Fine-grained Conditional Probability Estimation","created":"2025-05-02","cited_by_count":9,"area":null},{"id":"2204.04813","title":"Explanation Graph Generation via Pre-trained Language Models: An Empirical Study with Contrastive Learning","created":"2022-04-11","cited_by_count":8,"area":null},{"id":"2110.01509","title":"DeepA2: A Modular Framework for Deep Argument Analysis with Pretrained Neural Text2Text Language Models","created":"2021-10-04","cited_by_count":7,"area":null},{"id":"2210.17095","title":"RLET: A Reinforcement Learning Based Approach for Explainable QA with Entailment Trees","created":"2022-10-31","cited_by_count":7,"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":"2212.10618","title":"Ontologically Faithful Generation of Non-Player Character Dialogues","created":"2022-12-20","cited_by_count":7,"area":null},{"id":"2305.02993","title":"SemEval-2023 Task 7: Multi-Evidence Natural Language Inference for Clinical Trial Data","created":"2023-05-04","cited_by_count":7,"area":null},{"id":"2311.17438","title":"CLOMO: Counterfactual Logical Modification with Large Language Models","created":"2023-11-29","cited_by_count":7,"area":"lr"},{"id":"2402.06287","title":"AI, Meet Human: Learning Paradigms for Hybrid Decision Making Systems","created":"2024-02-09","cited_by_count":7,"area":null},{"id":"2404.18865","title":"Truth-value judgment in language models: 'truth directions' are context sensitive","created":"2024-04-29","cited_by_count":7,"area":null},{"id":"2211.07950","title":"Breakpoint Transformers for Modeling and Tracking Intermediate Beliefs","created":"2022-11-15","cited_by_count":6,"area":null},{"id":"2305.01713","title":"Learning Disentangled Semantic Spaces of Explanations via Invertible Neural Networks","created":"2023-05-02","cited_by_count":6,"area":null},{"id":"2311.08579","title":"Graph-Induced Syntactic-Semantic Spaces in Transformer-Based Variational AutoEncoders","created":"2023-11-14","cited_by_count":6,"area":null},{"id":"2402.00723","title":"Improving Semantic Control in Discrete Latent Spaces with Transformer Quantized Variational Autoencoders","created":"2024-02-01","cited_by_count":6,"area":null},{"id":"2601.20539","title":"PathWise: Planning through World Model for Automated Heuristic Design via Self-Evolving LLMs","created":"2026-01-28","cited_by_count":6,"area":"wm"},{"id":"2210.06230","title":"Quasi-symbolic Semantic Geometry over Transformer-based Variational AutoEncoder","created":"2022-10-12","cited_by_count":5,"area":null},{"id":"2306.04441","title":"STEPS: A Benchmark for Order Reasoning in Sequential Tasks","created":"2023-06-07","cited_by_count":5,"area":"lr"},{"id":"2401.04518","title":"The Critique of Critique","created":"2024-01-09","cited_by_count":5,"area":null},{"id":"2402.10767","title":"Inference to the Best Explanation in Large Language Models","created":"2024-02-16","cited_by_count":5,"area":null},{"id":"2502.16757","title":"Entailment-Preserving First-order Logic Representations in Natural Language Entailment","created":"2025-02-24","cited_by_count":5,"area":null},{"id":"2209.01824","title":"A Survey on Measuring and Mitigating Reasoning Shortcuts in Machine Reading Comprehension","created":"2022-09-05","cited_by_count":4,"area":null},{"id":"2311.09613","title":"Digital Socrates: Evaluating LLMs through Explanation Critiques","created":"2023-11-16","cited_by_count":4,"area":null},{"id":"2503.11348","title":"RESPONSE: Benchmarking the Ability of Language Models to Undertake Commonsense Reasoning in Crisis Situation","created":"2025-03-14","cited_by_count":4,"area":"lr"},{"id":"2204.06283","title":"Curriculum: A Broad-Coverage Benchmark for Linguistic Phenomena in Natural Language Understanding","created":"2022-04-13","cited_by_count":3,"area":null},{"id":"2210.12487","title":"MetaLogic: Logical Reasoning Explanations with Fine-Grained Structure","created":"2022-10-22","cited_by_count":3,"area":"lr"},{"id":"2212.03747","title":"Harnessing Knowledge and Reasoning for Human-Like Natural Language Generation: A Brief Review","created":"2022-12-07","cited_by_count":3,"area":null},{"id":"2307.02472","title":"Deductive Additivity for Planning of Natural Language Proofs","created":"2023-07-05","cited_by_count":3,"area":null}],"next_cursor":"100"}