{"total":29,"rows":[{"id":"2502.06737","title":"VersaPRM: Multi-Domain Process Reward Model via Synthetic Reasoning Data","created":"2025-02-10","cited_by_count":40,"area":"lr"},{"id":"2402.02805","title":"Graph-enhanced Large Language Models in Asynchronous Plan Reasoning","created":"2024-02-05","cited_by_count":37,"area":"lr"},{"id":"2507.23751","title":"CoT-Self-Instruct: Building high-quality synthetic prompts for reasoning and non-reasoning tasks","created":"2025-07-31","cited_by_count":32,"area":"lr"},{"id":"2502.01969","title":"Mitigating Object Hallucinations in Large Vision-Language Models via Attention Calibration","created":"2025-02-04","cited_by_count":23,"area":"lr"},{"id":"2305.01505","title":"Beyond Classification: Financial Reasoning in State-of-the-Art Language Models","created":"2023-04-30","cited_by_count":19,"area":"lr"},{"id":"2505.11595","title":"Stepwise Guided Policy Optimization: Coloring your Incorrect Reasoning in GRPO","created":"2025-05-16","cited_by_count":19,"area":"lr"},{"id":"2310.18440","title":"Modeling Legal Reasoning: LM Annotation at the Edge of Human Agreement","created":"2023-10-27","cited_by_count":17,"area":"lr"},{"id":"2405.13966","title":"On the Brittle Foundations of ReAct Prompting for Agentic Large Language Models","created":"2024-05-22","cited_by_count":17,"area":"lr"},{"id":"2502.12470","title":"Reasoning on a Spectrum: Aligning LLMs to System 1 and System 2 Thinking","created":"2025-02-18","cited_by_count":16,"area":"lr"},{"id":"2310.04484","title":"Ada-Instruct: Adapting Instruction Generators for Complex Reasoning","created":"2023-10-06","cited_by_count":11,"area":"lr"},{"id":"2508.07827","title":"Evaluating Large Language Models as Expert Annotators","created":"2025-08-11","cited_by_count":9,"area":"lr"},{"id":"2403.00994","title":"Leveraging Prompt-Based Large Language Models: Predicting Pandemic Health Decisions and Outcomes Through Social Media Language","created":"2024-03-01","cited_by_count":6,"area":"lr"},{"id":"2405.11912","title":"ARAIDA: Analogical Reasoning-Augmented Interactive Data Annotation","created":"2024-05-20","cited_by_count":6,"area":"lr"},{"id":"2411.00890","title":"Rethinking Scale: The Efficacy of Fine-Tuned Open-Source LLMs in Large-Scale Reproducible Social Science Research","created":"2024-10-31","cited_by_count":6,"area":"lr"},{"id":"2310.12049","title":"Concept-Guided Chain-of-Thought Prompting for Pairwise Comparison Scoring of Texts with Large Language Models","created":"2023-10-18","cited_by_count":5,"area":"lr"},{"id":"2509.26041","title":"Unspoken Hints: Accuracy Without Acknowledgement in LLM Reasoning","created":"2025-09-30","cited_by_count":4,"area":"lr"},{"id":"2504.10496","title":"ArXivBench: When You Should Avoid Using ChatGPT for Academic Writing","created":"2025-04-06","cited_by_count":3,"area":"lr"},{"id":"2404.12994","title":"Rethinking the Evaluation of Dialogue Systems: Effects of User Feedback on Crowdworkers and LLMs","created":"2024-04-19","cited_by_count":2,"area":"lr"},{"id":"2602.09832","title":"LLM Reasoning Predicts When Models Are Right: Evidence from Coding Classroom Discourse","created":"2026-02-10","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":"2608.25618","title":"AWM: Answerable Working Memory for Long-Document VQA Agents","created":"2026-08-26","cited_by_count":2,"area":"lr"},{"id":"2409.17588","title":"DualCoTs: Dual Chain-of-Thoughts Prompting for Sentiment Lexicon Expansion of Idioms","created":"2024-09-26","cited_by_count":1,"area":"lr"},{"id":"2510.16095","title":"Reliability of Large Language Model Generated Clinical Reasoning in Assisted Reproductive Technology: Blinded Comparative Evaluation Study","created":"2025-10-17","cited_by_count":1,"area":"lr"},{"id":"2409.17904","title":"Learning to Love Edge Cases in Formative Math Assessment: Using the AMMORE Dataset and Chain-of-Thought Prompting to Improve Grading Accuracy","created":"2024-09-26","cited_by_count":0,"area":"lr"},{"id":"2510.11190","title":"FlexAC: Towards Flexible Control of Associative Reasoning in Multimodal Large Language Models","created":"2025-10-13","cited_by_count":0,"area":"lr"},{"id":"2604.03374","title":"CresOWLve: Benchmarking Creative Problem-Solving Over Real-World Knowledge","created":"2026-04-03","cited_by_count":0,"area":"lr"},{"id":"2607.04945","title":"You Frame It: How Conceptual Representations Shape LLM Detection and Reasoning about Antisemitism","created":"2026-07-06","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":"2610.16182","title":"Label-Centric Knowledge Retrieval for Zero-Shot Text Classification","created":"2026-10-12","cited_by_count":0,"area":"lr"}],"next_cursor":null}