{"total":72,"rows":[{"id":"2411.19799","title":"INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge","created":"2024-11-29","cited_by_count":86,"area":null},{"id":"2510.17516","title":"SimBench: Benchmarking the Ability of Large Language Models to Simulate Human Behaviors","created":"2025-10-20","cited_by_count":52,"area":null},{"id":"2503.03064","title":"Improving LLM-as-a-Judge Inference with the Judgment Distribution","created":"2025-03-04","cited_by_count":37,"area":null},{"id":"2409.15277","title":"A Preliminary Study of o1 in Medicine: Are We Closer to an AI Doctor?","created":"2024-09-23","cited_by_count":33,"area":null},{"id":"2508.10047","title":"A Survey of Optimization Modeling Meets LLMs: Progress and Future Directions","created":"2025-08-12","cited_by_count":31,"area":null},{"id":"2410.14826","title":"SPRIG: Improving Large Language Model Performance by System Prompt Optimization","created":"2024-10-18","cited_by_count":29,"area":null},{"id":"2502.04506","title":"When One LLM Drools, Multi-LLM Collaboration Rules","created":"2025-02-06","cited_by_count":28,"area":null},{"id":"2502.11677","title":"Towards Fully Exploiting LLM Internal States to Enhance Knowledge Boundary Perception","created":"2025-02-17","cited_by_count":27,"area":null},{"id":"2501.04961","title":"Demystifying Domain-adaptive Post-training for Financial LLMs","created":"2025-01-09","cited_by_count":24,"area":null},{"id":"2502.04510","title":"Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems","created":"2025-02-06","cited_by_count":23,"area":null},{"id":"2510.06826","title":"Mid-Training of Large Language Models: A Survey","created":"2025-10-08","cited_by_count":21,"area":null},{"id":"2502.11027","title":"On the Effect of Sampling Diversity in Scaling LLM Inference","created":"2025-02-16","cited_by_count":18,"area":null},{"id":"2505.17968","title":"Are Large Language Models Reliable AI Scientists? Assessing Reverse-Engineering of Black-Box Systems","created":"2025-05-23","cited_by_count":14,"area":null},{"id":"2502.16435","title":"Human Cognitive Benchmarks Reveal Foundational Visual Gaps in MLLMs","created":"2025-02-23","cited_by_count":13,"area":null},{"id":"2508.02721","title":"Blueprint First, Model Second: A Framework for Deterministic LLM Workflow","created":"2025-08-01","cited_by_count":12,"area":null},{"id":"2604.16027","title":"Where does output diversity collapse in post-training?","created":"2026-04-17","cited_by_count":11,"area":null},{"id":"2504.05089","title":"Climplicit: Climatic Implicit Embeddings for Global Ecological Tasks","created":"2025-04-07","cited_by_count":10,"area":null},{"id":"2502.16671","title":"MimeQA: Towards Socially-Intelligent Nonverbal Foundation Models","created":"2025-02-23","cited_by_count":9,"area":null},{"id":"2502.16706","title":"DISC: Dynamic Decomposition Improves LLM Inference Scaling","created":"2025-02-23","cited_by_count":9,"area":null},{"id":"2505.16303","title":"INFERENCEDYNAMICS: Efficient Routing Across LLMs through Structured Capability and Knowledge Profiling","created":"2025-05-22","cited_by_count":8,"area":null},{"id":"2510.11586","title":"Survey Response Generation: Generating Closed-Ended Survey Responses In-Silico with Large Language Models","created":"2025-10-13","cited_by_count":8,"area":null},{"id":"2602.23163","title":"A Decision-Theoretic Formalisation of Steganography With Applications to LLM Monitoring","created":"2026-02-26","cited_by_count":8,"area":null},{"id":"2410.05262","title":"TurtleBench: Evaluating Top Language Models via Real-World Yes/No Puzzles","created":"2024-10-07","cited_by_count":7,"area":null},{"id":"2410.16270","title":"Reflection-Bench: Evaluating Epistemic Agency in Large Language Models","created":"2024-10-21","cited_by_count":7,"area":null},{"id":"2506.00309","title":"Evaluation of LLMs for mathematical problem solving","created":"2025-05-30","cited_by_count":7,"area":null},{"id":"2506.03984","title":"Around the World in 24 Hours: Probing LLM Knowledge of Time and Place","created":"2025-06-04","cited_by_count":7,"area":null},{"id":"2509.24216","title":"MoVa: Towards Generalizable Classification of Human Morals and Values","created":"2025-09-29","cited_by_count":7,"area":null},{"id":"2603.05923","title":"Learning Next Action Predictors from Human-Computer Interaction","created":"2026-03-06","cited_by_count":7,"area":null},{"id":"2606.17930","title":"How Inference Compute Shapes Frontier LLM Evaluation","created":"2026-06-16","cited_by_count":7,"area":null},{"id":"2504.19898","title":"GenCLS++: Pushing the Boundaries of Generative Classification in LLMs Through Comprehensive SFT and RL Studies Across Diverse Datasets","created":"2025-04-28","cited_by_count":6,"area":null},{"id":"2503.13992","title":"The KoLMogorov Test: Compression by Code Generation","created":"2025-03-18","cited_by_count":5,"area":null},{"id":"2412.17729","title":"Chumor 2.0: Towards Benchmarking Chinese Humor Understanding","created":"2024-12-23","cited_by_count":4,"area":null},{"id":"2509.19358","title":"Benchmarking and Improving LLM Robustness for Personalized Generation","created":"2025-09-18","cited_by_count":4,"area":null},{"id":"2602.16162","title":"LLMs Exhibit Significantly Lower Uncertainty in Creative Writing Than Professional Writers","created":"2026-02-18","cited_by_count":4,"area":null},{"id":"2501.09265","title":"Perspective Transition of Large Language Models for Solving Subjective Tasks","created":"2025-01-16","cited_by_count":3,"area":null},{"id":"2502.18791","title":"Can LLMs Help Uncover Insights about LLMs? A Large-Scale, Evolving Literature Analysis of Frontier LLMs","created":"2025-02-26","cited_by_count":3,"area":null},{"id":"2503.10542","title":"Language Models, Graph Searching, and Supervision Adulteration: When More Supervision is Less and How to Make More More","created":"2025-03-13","cited_by_count":3,"area":null},{"id":"2511.08877","title":"Hierarchical Memorization in Large Language Models: Evidence from Citation Generation","created":"2025-11-12","cited_by_count":3,"area":null},{"id":"2511.20836","title":"Structured Prompts Improve Evaluation of Language Models","created":"2025-11-25","cited_by_count":3,"area":null},{"id":"2604.09237","title":"ScheMatiQ: From Research Question to Structured Data through Interactive Schema Discovery","created":"2026-04-10","cited_by_count":3,"area":null},{"id":"2410.15966","title":"Self-Explained Keywords Empower Large Language Models for Code Generation","created":"2024-10-21","cited_by_count":2,"area":null},{"id":"2412.01340","title":"A 2-step Framework for Automated Literary Translation Evaluation: Its Promises and Pitfalls","created":"2024-12-02","cited_by_count":2,"area":null},{"id":"2507.02529","title":"RetrySQL: text-to-SQL training with retry data for self-correcting query generation","created":"2025-07-03","cited_by_count":2,"area":null},{"id":"2509.26136","title":"CliniBench: A Clinical Outcome Prediction Benchmark for Generative and Encoder-Based Language Models","created":"2025-09-30","cited_by_count":2,"area":null},{"id":"2510.12699","title":"Generation Space Size: Understanding and Calibrating Open-Endedness of LLM Generations","created":"2025-10-14","cited_by_count":2,"area":null},{"id":"2511.07722","title":"Critical Confabulation: Can LLMs Hallucinate for Social Good?","created":"2025-11-11","cited_by_count":2,"area":null},{"id":"2604.10027","title":"SinkTrack: Attention Sink based Context Anchoring for Large Language Models","created":"2026-04-11","cited_by_count":2,"area":null},{"id":"2605.01011","title":"CLEAR: Revealing How Noise and Ambiguity Degrade Reliability in LLMs for Medicine","created":"2026-05-01","cited_by_count":2,"area":null},{"id":"2605.05715","title":"Decodable but Not Corrected by Fixed Residual-Stream Linear Steering: Evidence from Medical LLM Failure Regimes","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2606.10142","title":"DB-3DME: From Dataset to Benchmark for Human-aligned Automatic 3D Mesh Evaluation","created":"2026-06-08","cited_by_count":2,"area":null},{"id":"2409.17005","title":"Models Can and Should Embrace the Communicative Nature of Human-Generated Math","created":"2024-09-25","cited_by_count":1,"area":null},{"id":"2410.14979","title":"Do Large Language Models Truly Grasp Mathematics? An Empirical Exploration From Cognitive Psychology","created":"2024-10-19","cited_by_count":1,"area":null},{"id":"2505.24147","title":"Rationales Are Not Silver Bullets: Measuring the Impact of Rationales on Model Performance and Reliability","created":"2025-05-30","cited_by_count":1,"area":null},{"id":"2508.18244","title":"Type-Compliant Adaptation Cascades: Adapting Programmatic LM Workflows to Data","created":"2025-08-25","cited_by_count":1,"area":null},{"id":"2510.00449","title":"Enhancing Rating Prediction with Off-the-Shelf LLMs Using In-Context User Reviews","created":"2025-10-01","cited_by_count":1,"area":null},{"id":"2604.21354","title":"Decoupled Travel Planning with Behavior Forest","created":"2026-04-23","cited_by_count":1,"area":null},{"id":"2605.11260","title":"Curriculum Learning-Guided Progressive Distillation in Large Language Models","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2502.16717","title":"Beyond Pattern Recognition: Probing Mental Representations of LMs","created":"2025-02-23","cited_by_count":0,"area":null},{"id":"2506.19889","title":"Retrieval-Confused Generation is a Good Defender for Privacy Violation Attack of Large Language Models","created":"2025-06-24","cited_by_count":0,"area":null},{"id":"2510.10142","title":"Debiasing LLMs by Masking Unfairness-Driving Attention Heads","created":"2025-10-11","cited_by_count":0,"area":null},{"id":"2602.06015","title":"A Systematic Evaluation of Large Language Models for PTSD Severity Estimation: The Role of Contextual Knowledge and Modeling Strategies","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2603.26898","title":"Magic Words or Methodical Work? Challenging Conventional Wisdom in LLM-Based Political Text Annotation","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2605.13138","title":"A Comprehensive Evaluation of Code Language Models for Security Patch Detection","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2606.21008","title":"The Metanym Game: An LLM Benchmark Without Ground Truth That Rises With the Models It Measures","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2607.08018","title":"Concretized Proposition Prompting Resolves Composition-Knowledge Dichotomy in Large Language Models","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2608.28021","title":"Compared to What? A Human-Anchored Security Benchmark for LLM-Generated Infrastructure-as-Code","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2608.30021","title":"Error Detection for PET/CT Radiology Reports: Domain-Specific vs Large Language Models","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.14142","title":"T-SMART: Mechanism-Level Attribution for Tool-Augmented Time-Series Question Answering","created":"2026-09-12","cited_by_count":0,"area":null},{"id":"2609.22249","title":"A Tutorial on Prompt Engineering: From Messy Thoughts to AI Workflows","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2610.13625","title":"Kernel-based External Validity of Experimental Studies","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.13999","title":"SemTree: Judge-Aware Semantic Decision Trees for Inspectable and Repairable Rule Decisions","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.16713","title":"Audit Before You Distill: A Controlled Workflow for Reasoning Transfer into Compact Medical Language Models","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}