{"total":58,"rows":[{"id":"2305.12744","title":"Fact-Checking Complex Claims with Program-Guided Reasoning","created":"2023-05-22","cited_by_count":146,"area":"lr"},{"id":"2310.14799","title":"Cross-lingual Prompting: Improving Zero-shot Chain-of-Thought Reasoning across Languages","created":"2023-10-23","cited_by_count":97,"area":"lr"},{"id":"2305.04808","title":"CAT: A Contextualized Conceptualization and Instantiation Framework for Commonsense Reasoning","created":"2023-05-08","cited_by_count":25,"area":"lr"},{"id":"2401.17686","title":"Deductive Beam Search: Decoding Deducible Rationale for Chain-of-Thought Reasoning","created":"2024-01-31","cited_by_count":24,"area":"lr"},{"id":"2307.01640","title":"Chain of Thought Prompting Elicits Knowledge Augmentation","created":"2023-07-04","cited_by_count":21,"area":"lr"},{"id":"2203.11130","title":"PACS: A Dataset for Physical Audiovisual CommonSense Reasoning","created":"2022-03-21","cited_by_count":18,"area":"lr"},{"id":"2206.01532","title":"Acquiring and Modelling Abstract Commonsense Knowledge via Conceptualization","created":"2022-06-03","cited_by_count":17,"area":"lr"},{"id":"2305.02556","title":"Faithful Question Answering with Monte-Carlo Planning","created":"2023-05-04","cited_by_count":16,"area":"lr"},{"id":"2306.09237","title":"One Law, Many Languages: Benchmarking Multilingual Legal Reasoning for Judicial Support","created":"2023-06-15","cited_by_count":16,"area":"lr"},{"id":"2502.19587","title":"NeoBERT: A Next-Generation BERT","created":"2025-02-26","cited_by_count":16,"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":"2502.20592","title":"Multi2: Multi-Agent Test-Time Scalable Framework for Multi-Document Processing","created":"2025-02-27","cited_by_count":12,"area":"lr"},{"id":"2509.21164","title":"Mixture of Thoughts: Learning to Aggregate What Experts Think, Not Just What They Say","created":"2025-09-25","cited_by_count":12,"area":"lr"},{"id":"2406.02106","title":"MARS: Benchmarking the Metaphysical Reasoning Abilities of Language Models with a Multi-task Evaluation Dataset","created":"2024-06-04","cited_by_count":11,"area":"lr"},{"id":"2410.00751","title":"Thinking Outside of the Differential Privacy Box: A Case Study in Text Privatization with Language Model Prompting","created":"2024-10-01","cited_by_count":11,"area":"lr"},{"id":"2506.09958","title":"Kvasir-VQA-x1: A Multimodal Dataset for Medical Reasoning and Robust MedVQA in Gastrointestinal Endoscopy","created":"2025-06-11","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":"2506.19467","title":"Can Reasoning Help Large Language Models Capture Human Annotator Disagreement?","created":"2025-06-24","cited_by_count":10,"area":"lr"},{"id":"2404.00209","title":"EventGround: Narrative Reasoning by Grounding to Eventuality-centric Knowledge Graphs","created":"2024-03-30","cited_by_count":9,"area":"lr"},{"id":"2501.09957","title":"FRAG: A Flexible Modular Framework for Retrieval-Augmented Generation based on Knowledge Graphs","created":"2025-01-17","cited_by_count":8,"area":"lr"},{"id":"2502.19230","title":"Two Heads Are Better Than One: Dual-Model Verbal Reflection at Inference-Time","created":"2025-02-26","cited_by_count":8,"area":"lr"},{"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":"2310.05450","title":"Empower Nested Boolean Logic via Self-Supervised Curriculum Learning","created":"2023-10-09","cited_by_count":7,"area":"lr"},{"id":"2402.03469","title":"Rethinking the Role of Proxy Rewards in Language Model Alignment","created":"2024-02-02","cited_by_count":7,"area":"lr"},{"id":"2212.09282","title":"APOLLO: A Simple Approach for Adaptive Pretraining of Language Models for Logical Reasoning","created":"2022-12-19","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":"2603.20895","title":"LLM Router: Rethinking Routing with Prefill Activations","created":"2026-03-21","cited_by_count":5,"area":"lr"},{"id":"2310.12011","title":"Gold: A Global and Local-aware Denoising Framework for Commonsense Knowledge Graph Noise Detection","created":"2023-10-18","cited_by_count":4,"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":"2401.13246","title":"SEER: Facilitating Structured Reasoning and Explanation via Reinforcement Learning","created":"2024-01-24","cited_by_count":3,"area":"lr"},{"id":"2406.11035","title":"Scaling Synthetic Logical Reasoning Datasets with Context-Sensitive Declarative Grammars","created":"2024-06-16","cited_by_count":3,"area":"lr"},{"id":"2411.01093","title":"TabVer: Tabular Fact Verification with Natural Logic","created":"2024-11-02","cited_by_count":3,"area":"lr"},{"id":"2607.05861","title":"Mitigating Factual Hallucination in Large Reasoning Models via Mixed-Mode Advantage Regularization","created":"2026-07-07","cited_by_count":3,"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":"2502.06487","title":"Adaptive Prompting: Ad-hoc Prompt Composition for Social Bias Detection","created":"2025-02-10","cited_by_count":2,"area":"lr"},{"id":"2508.18676","title":"Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding","created":"2025-08-26","cited_by_count":2,"area":"lr"},{"id":"2510.08592","title":"Less Diverse, Less Safe: The Indirect But Pervasive Risk of Test-Time Scaling in Large Language Models","created":"2025-10-04","cited_by_count":2,"area":"lr"},{"id":"2510.13157","title":"Program of Thoughts for Financial Reasoning: Leveraging Dynamic In-Context Examples and Generative Retrieval","created":"2025-10-15","cited_by_count":2,"area":"lr"},{"id":"2511.07397","title":"Thinking While Speaking: Inference-Time Knowledge Transfer for Responsive and Intelligent Conversational Voice Agents","created":"2025-11-10","cited_by_count":2,"area":"lr"},{"id":"2605.18871","title":"Distributional Energy-Based Models for Uncertainty-Aware Structured LLM Reasoning","created":"2026-05-15","cited_by_count":2,"area":"lr"},{"id":"2404.01084","title":"AILS-NTUA at SemEval-2024 Task 9: Cracking Brain Teasers: Transformer Models for Lateral Thinking Puzzles","created":"2024-04-01","cited_by_count":1,"area":"lr"},{"id":"2412.08317","title":"Large Language Models Still Face Challenges in Multi-Hop Reasoning with External Knowledge","created":"2024-12-11","cited_by_count":1,"area":"lr"},{"id":"2503.17136","title":"CoKe: Customizable Fine-Grained Story Evaluation via Chain-of-Keyword Rationalization","created":"2025-03-21","cited_by_count":1,"area":"lr"},{"id":"2504.14905","title":"CRAVE: A Conflicting Reasoning Approach for Explainable Claim Verification Using LLMs","created":"2025-04-21","cited_by_count":1,"area":"lr"},{"id":"2508.06671","title":"Do Biased Models Have Biased Thoughts?","created":"2025-08-08","cited_by_count":1,"area":"lr"},{"id":"2608.15056","title":"GraphLoom: Reliability-Calibrated Graph Evidence Routing for Multimodal KG-RAG","created":"2026-08-15","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":"2310.06803","title":"Advancing Transformer's Capabilities in Commonsense Reasoning","created":"2023-10-10","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":"2601.16504","title":"LOGICAL-COMMONSENSEQA: A Benchmark for Logical Commonsense Reasoning","created":"2026-01-23","cited_by_count":0,"area":"lr"},{"id":"2604.15648","title":"HyperGVL: Benchmarking and Improving Large Vision-Language Models in Hypergraph Understanding and Reasoning","created":"2026-04-17","cited_by_count":0,"area":"lr"},{"id":"2605.30214","title":"GRUFF: LLM Pronoun Fidelity, Reasoning, and Biases in German","created":"2026-05-28","cited_by_count":0,"area":"lr"},{"id":"2607.11207","title":"ProgramTab: Boosting Table Reasoning of LLMs via Programmatic Paradigm","created":"2026-07-13","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":"2608.12877","title":"ReflectFact: Self-Reflective Agents for Improving Comprehension and Reasoning in Multi-Hop Fact Verification","created":"2026-08-13","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":"2610.03565","title":"Writerslogic at PAN 2026: Process over Content for Robust Detection under Domain Shift","created":"2026-10-02","cited_by_count":0,"area":"lr"},{"id":"2610.15091","title":"Have You Been Convinced? A Neuro-symbolic Argumentation Reasoning Approach to Detecting Persuasiveness in ChangeMyView Discussions","created":"2026-10-10","cited_by_count":0,"area":"lr"}],"next_cursor":null}