{"total":97,"rows":[{"id":"2408.05109","title":"A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?","created":"2024-08-09","cited_by_count":56,"area":null},{"id":"2506.07295","title":"Exploring the Impact of Temperature on Large Language Models:Hot or Cold?","created":"2025-06-08","cited_by_count":40,"area":null},{"id":"2403.09732","title":"PET-SQL: A Prompt-Enhanced Two-Round Refinement of Text-to-SQL with Cross-consistency","created":"2024-03-13","cited_by_count":27,"area":null},{"id":"2503.21411","title":"Exploring the Roles of Large Language Models in Reshaping Transportation Systems: A Survey, Framework, and Roadmap","created":"2025-03-27","cited_by_count":26,"area":null},{"id":"2502.05196","title":"LLMs Provide Unstable Answers to Legal Questions","created":"2025-01-28","cited_by_count":19,"area":null},{"id":"2510.01218","title":"Control the Temperature: Selective Sampling for Diverse and High-Quality LLM Outputs","created":"2025-09-20","cited_by_count":15,"area":null},{"id":"2511.00432","title":"G2: Guided Generation for Enhanced Output Diversity in LLMs","created":"2025-11-01","cited_by_count":14,"area":null},{"id":"2502.07508","title":"Enhance-A-Video: Better Generated Video for Free","created":"2025-02-11","cited_by_count":11,"area":null},{"id":"2503.00691","title":"How Diversely Can Language Models Solve Problems? Exploring the Algorithmic Diversity of Model-Generated Code","created":"2025-03-02","cited_by_count":11,"area":null},{"id":"2604.11581","title":"Hidden Measurement Error in LLM Pipelines Distorts Annotation, Evaluation, and Benchmarking","created":"2026-04-13","cited_by_count":10,"area":null},{"id":"2411.03495","title":"Automatic Generation of Question Hints for Mathematics Problems using Large Language Models in Educational Technology","created":"2024-11-05","cited_by_count":9,"area":null},{"id":"2506.23601","title":"Semantic-guided Diverse Decoding for Large Language Model","created":"2025-06-30","cited_by_count":9,"area":null},{"id":"2412.00868","title":"Quantifying perturbation impacts for large language models","created":"2024-12-01","cited_by_count":8,"area":null},{"id":"2506.07947","title":"Statistical Hypothesis Testing for Auditing Robustness in Language Models","created":"2025-06-09","cited_by_count":8,"area":null},{"id":"2508.00033","title":"GPT-4.1 Sets the Standard in Automated Experiment Design Using Novel Python Libraries","created":"2025-07-30","cited_by_count":8,"area":null},{"id":"2601.21895","title":"Learn-to-Distance: Distance Learning for Detecting LLM-Generated Text","created":"2026-01-29","cited_by_count":8,"area":null},{"id":"2506.14276","title":"Don't throw the baby out with the bathwater: How and why deep learning for ARC","created":"2025-06-17","cited_by_count":7,"area":null},{"id":"2602.13540","title":"On Calibration of Large Language Models: From Response To Capability","created":"2026-02-14","cited_by_count":7,"area":null},{"id":"2603.14893","title":"LLMs as Signal Detectors: Sensitivity, Bias, and the Temperature-Criterion Analogy","created":"2026-03-16","cited_by_count":7,"area":null},{"id":"2504.12320","title":"Has the Creativity of Large-Language Models peaked? An analysis of inter- and intra-LLM variability","created":"2025-04-10","cited_by_count":6,"area":null},{"id":"2506.00400","title":"Scaling Textual Gradients via Sampling-Based Momentum","created":"2025-05-31","cited_by_count":6,"area":null},{"id":"2508.12040","title":"Mind the Generation Process: Fine-Grained Confidence Estimation During LLM Generation","created":"2025-08-16","cited_by_count":6,"area":null},{"id":"2411.13244","title":"Leveraging Prior Experience: An Expandable Auxiliary Knowledge Base for Text-to-SQL","created":"2024-11-20","cited_by_count":5,"area":null},{"id":"2506.14092","title":"Fragile Preferences: A Deep Dive Into Order Effects in Large Language Models","created":"2025-06-17","cited_by_count":5,"area":null},{"id":"2507.02226","title":"DecoRTL: A Run-time Decoding Framework for RTL Code Generation with LLMs","created":"2025-07-03","cited_by_count":5,"area":null},{"id":"2509.08480","title":"Acquiescence Bias in Large Language Models","created":"2025-09-10","cited_by_count":5,"area":null},{"id":"2512.23712","title":"STED and Consistency Scoring: A Framework for Evaluating LLM Structured Output Reliability","created":"2025-11-27","cited_by_count":5,"area":null},{"id":"2411.09255","title":"DAHL: Domain-specific Automated Hallucination Evaluation of Long-Form Text through a Benchmark Dataset in Biomedicine","created":"2024-11-14","cited_by_count":4,"area":null},{"id":"2501.09126","title":"Augmenting Human-Annotated Training Data with Large Language Model Generation and Distillation in Open-Response Assessment","created":"2025-01-15","cited_by_count":4,"area":null},{"id":"2503.03170","title":"AttackSeqBench: Benchmarking the Capabilities of LLMs for Attack Sequences Understanding","created":"2025-03-05","cited_by_count":4,"area":null},{"id":"2505.03988","title":"Can Large Language Models Predict Parallel Code Performance?","created":"2025-05-06","cited_by_count":4,"area":null},{"id":"2505.23838","title":"Exploring the Landscape of Text-to-SQL with Large Language Models: Progresses, Challenges and Opportunities","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2508.20186","title":"AI Propaganda factories with language models","created":"2025-08-27","cited_by_count":4,"area":null},{"id":"2501.16309","title":"Evaluating The Performance of Using Large Language Models to Automate Summarization of CT Simulation Orders in Radiation Oncology","created":"2025-01-27","cited_by_count":3,"area":null},{"id":"2509.14899","title":"CARGO: A Framework for Confidence-Aware Routing of Large Language Models","created":"2025-09-18","cited_by_count":3,"area":null},{"id":"2510.18908","title":"Improving Topic Modeling of Social Media Short Texts with Rephrasing: A Case Study of COVID-19 Related Tweets","created":"2025-10-21","cited_by_count":3,"area":null},{"id":"2602.17445","title":"ABCD: All Biases Come Disguised","created":"2026-02-19","cited_by_count":3,"area":null},{"id":"2603.28304","title":"The Necessity of Setting Temperature in LLM-as-a-Judge","created":"2026-03-30","cited_by_count":3,"area":null},{"id":"2410.08058","title":"Closing the Loop: Learning to Generate Writing Feedback via Language Model Simulated Student Revisions","created":"2024-10-10","cited_by_count":2,"area":null},{"id":"2501.05601","title":"Exploring Large Language Models for Translating Romanian Computational Problems into English","created":"2025-01-09","cited_by_count":2,"area":null},{"id":"2505.10013","title":"DIF: A Framework for Benchmarking and Verifying Implicit Bias in LLMs","created":"2025-05-15","cited_by_count":2,"area":null},{"id":"2507.15157","title":"Can LLMs Generate User Stories and Assess Their Quality?","created":"2025-07-20","cited_by_count":2,"area":null},{"id":"2507.15715","title":"From Queries to Criteria: Understanding How Astronomers Evaluate LLMs","created":"2025-07-21","cited_by_count":2,"area":null},{"id":"2512.21635","title":"Heaven-Sent or Hell-Bent? Benchmarking the Intelligence and Defectiveness of LLM Hallucinations","created":"2025-12-25","cited_by_count":2,"area":null},{"id":"2602.16811","title":"Evaluating Monolingual and Multilingual Large Language Models for Greek Question Answering: The DemosQA Benchmark","created":"2026-02-18","cited_by_count":2,"area":null},{"id":"2605.25773","title":"Efficient Benchmarking Is Just Feature Selection and Multiple Regression","created":"2026-05-25","cited_by_count":2,"area":null},{"id":"2606.27687","title":"Mitigating LLM-based p-Hacking by Preregistering for the Next LLM","created":"2026-06-26","cited_by_count":2,"area":null},{"id":"2609.04047","title":"The Dice Roll Method: A Standardized Protocol for Repeated-Query Auditing of Large Language Model Brand Recommendations","created":"2026-09-03","cited_by_count":2,"area":null},{"id":"2411.07441","title":"Automatically Detecting Online Deceptive Patterns","created":"2024-11-11","cited_by_count":1,"area":null},{"id":"2504.08779","title":"Can AI Master Construction Management (CM)? Benchmarking State-of-the-Art Large Language Models on CM Certification Exams","created":"2025-04-04","cited_by_count":1,"area":null},{"id":"2505.23386","title":"VModA: An Effective Framework for Adaptive NSFW Image Moderation","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2506.10572","title":"Probability Bounding: Post-Hoc Calibration via Box-Constrained Softmax","created":"2025-06-12","cited_by_count":1,"area":null},{"id":"2507.13550","title":"GOFAI meets Generative AI: Development of Expert Systems by means of Large Language Models","created":"2025-07-17","cited_by_count":1,"area":null},{"id":"2508.04755","title":"Are Large Language Models Dynamic Treatment Planners? An In Silico Study from a Prior Knowledge Injection Angle","created":"2025-08-06","cited_by_count":1,"area":null},{"id":"2509.23108","title":"Artificial Phantasia: Emergent Mental Imagery in Large Language Models","created":"2025-09-27","cited_by_count":1,"area":null},{"id":"2511.01292","title":"Optimal Attention Temperature Improves the Robustness of In-Context Learning under Distribution Shift in High Dimensions","created":"2025-11-03","cited_by_count":1,"area":null},{"id":"2511.16832","title":"The Shifting Landscape of Vaccine Discourse: Insights From a Decade of Pre- to Post-COVID-19 Vaccine Posts on Social Media","created":"2025-11-20","cited_by_count":1,"area":null},{"id":"2602.06665","title":"Not All Layers Need Tuning: Selective Layer Restoration Recovers Diversity","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2603.07717","title":"Rigidity in LLM Bandits with Implications for Human-AI Dyads","created":"2026-03-08","cited_by_count":1,"area":null},{"id":"2603.25269","title":"When Hate Meets Facts: LLMs-in-the-Loop for Check-worthiness Detection in Hate Speech","created":"2026-03-26","cited_by_count":1,"area":null},{"id":"2603.28643","title":"The Ultimate Tutorial for AI-driven Scale Development in Generative Psychometrics: Releasing AIGENIE from its Bottle","created":"2026-03-30","cited_by_count":1,"area":null},{"id":"2604.05461","title":"Content Fuzzing for Escaping Information Cocoons on Digital Social Media","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2604.10667","title":"Learning and Enforcing Context-Sensitive Control for LLMs","created":"2026-04-12","cited_by_count":1,"area":null},{"id":"2604.27006","title":"Beyond Accuracy: LLM Variability in Evidence Screening for Software Engineering SLRs","created":"2026-04-29","cited_by_count":1,"area":null},{"id":"2605.29979","title":"Fingerprinting Inference Systems of Large Language Models","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2607.05552","title":"The yes-no bias of large language models reflects answer order and wording, not shifts in moral judgment","created":"2026-07-06","cited_by_count":1,"area":null},{"id":"2608.14065","title":"Rethinking Automated Program Repair: The Impact of Bug Complexity, Fault Localization, and LLM Cost-efficiency","created":"2026-08-14","cited_by_count":1,"area":null},{"id":"2608.17516","title":"Effects of Answer Format Variation on Gender Bias in Large Language Models","created":"2026-08-18","cited_by_count":1,"area":null},{"id":"2409.09054","title":"Evaluating the Performance of Large Language Models in Competitive Programming: A Multi-Year, Multi-Grade Analysis","created":"2024-08-31","cited_by_count":0,"area":null},{"id":"2411.06722","title":"Synthesize, Partition, then Adapt: Eliciting Diverse Samples from Foundation Models","created":"2024-11-11","cited_by_count":0,"area":null},{"id":"2504.15392","title":"Tell Me What You Know About Sexism: Expert-LLM Interaction Strategies and Co-Created Definitions for Zero-Shot Sexism Detection","created":"2025-04-21","cited_by_count":0,"area":null},{"id":"2507.05279","title":"ReservoirChat: Interactive Documentation Enhanced with LLM and Knowledge Graph for ReservoirPy","created":"2025-07-04","cited_by_count":0,"area":null},{"id":"2507.19537","title":"Mind the Language Gap in Digital Humanities: LLM-Aided Translation of SKOS Thesauri","created":"2025-07-22","cited_by_count":0,"area":null},{"id":"2509.01962","title":"DRAssist: Dispute Resolution Assistance using Large Language Models","created":"2025-09-02","cited_by_count":0,"area":null},{"id":"2510.13143","title":"Stable LLM Ensemble: Interaction between Example Representativeness and Diversity","created":"2025-10-15","cited_by_count":0,"area":null},{"id":"2511.10876","title":"Architecting software monitors for control-flow anomaly detection through large language models and conformance checking","created":"2025-11-14","cited_by_count":0,"area":null},{"id":"2511.19464","title":"Temperature in SLMs: Impact on Incident Categorization in On-Premises Environments","created":"2025-11-21","cited_by_count":0,"area":null},{"id":"2601.12419","title":"Legal Experts Disagree With Rationale Extraction Techniques for Explaining ECtHR Case Outcome Classification","created":"2026-01-18","cited_by_count":0,"area":null},{"id":"2603.13698","title":"SAATT Nav: a Socially Aware Autonomous Transparent Transportation Navigation Framework for Wheelchairs","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2603.17021","title":"Generative AI-assisted Participatory Modeling in Socio-Environmental Planning under Deep Uncertainty","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2603.20225","title":"The Arrival of AGI? When Expert Personas Exceed Expert Benchmarks","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2603.24767","title":"Fine-Tuning A Large Language Model for Systematic Review Screening","created":"2026-03-25","cited_by_count":0,"area":null},{"id":"2604.14672","title":"SPAGBias: Uncovering and Tracing Structured Spatial Gender Bias in Large Language Models","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2604.17244","title":"DORA Explorer: Improving the Exploration Ability of LLMs Without Training","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2604.25927","title":"Information Extraction from Electricity Invoices with General-Purpose Large Language Models","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2605.10808","title":"Threat Modelling using Domain-Adapted Language Models: Empirical Evaluation and Insights","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.11188","title":"Adversarial SQL Injection Generation with LLM-Based Architectures","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.16538","title":"LLMs in Qualitative Research: Opportunities, Limitations, and Practical Considerations","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2605.16996","title":"Evaluation Drift in LLM Personality Induction: Are We Moving the Goalpost?","created":"2026-05-16","cited_by_count":0,"area":null},{"id":"2606.21937","title":"Latent Confidence Alignment for LLM Self-Assessment","created":"2026-06-20","cited_by_count":0,"area":null},{"id":"2607.03882","title":"Consistent but Miscalibrated: Evaluating LLM Limitations for Risk Communication in Natural Language","created":"2026-07-04","cited_by_count":0,"area":null},{"id":"2607.05761","title":"Synthetic Consumer Insight Generation with Large Language Models","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2607.12195","title":"Comparing Semantic Navigation in Humans and Large Language Models using Natural Language Processing","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2607.20429","title":"More Is Not More: What Matters for Diversity in LLM Opinions?","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2608.22758","title":"XTC: Head-Aware Sampling by Excluding Top Choices","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.07290","title":"Quality Metrics for LLM-Generated Asset Administration Shells: A Perturbation-Based Evaluation Approach","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2610.03095","title":"Peer Influence across Heterogeneous AI Models","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}