{"total":142,"rows":[{"id":"2407.21772","title":"ShieldGemma: Generative AI Content Moderation Based on Gemma","created":"2024-07-31","cited_by_count":243,"area":null},{"id":"2411.03350","title":"A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthiness","created":"2024-11-04","cited_by_count":127,"area":null},{"id":"2508.03682","title":"Self-Questioning Language Models","created":"2025-08-05","cited_by_count":50,"area":null},{"id":"2409.11404","title":"AraDiCE: Benchmarks for Dialectal and Cultural Capabilities in LLMs","created":"2024-09-17","cited_by_count":46,"area":null},{"id":"2409.06857","title":"What is the Role of Small Models in the LLM Era: A Survey","created":"2024-09-10","cited_by_count":41,"area":null},{"id":"2410.15413","title":"A Comprehensive Evaluation of Cognitive Biases in LLMs","created":"2024-10-20","cited_by_count":34,"area":null},{"id":"2503.04176","title":"TIMER: Temporal Instruction Modeling and Evaluation for Longitudinal Clinical Records","created":"2025-03-06","cited_by_count":34,"area":null},{"id":"2502.12378","title":"Pragmatics in the Era of Large Language Models: A Survey on Datasets, Evaluation, Opportunities and Challenges","created":"2025-02-17","cited_by_count":31,"area":null},{"id":"2412.11142","title":"AD-LLM: Benchmarking Large Language Models for Anomaly Detection","created":"2024-12-15","cited_by_count":26,"area":null},{"id":"2503.13502","title":"Foundation Models for Spatio-Temporal Data Science: A Tutorial and Survey","created":"2025-03-12","cited_by_count":24,"area":null},{"id":"2504.14757","title":"SWE-Synth: Synthesizing Verifiable Bug-Fix Data to Enable Large Language Models in Resolving Real-World Bugs","created":"2025-04-20","cited_by_count":22,"area":null},{"id":"2503.11441","title":"D3: Diversity, Difficulty, and Dependability-Aware Data Selection for Sample-Efficient LLM Instruction Tuning","created":"2025-03-14","cited_by_count":21,"area":null},{"id":"2412.10136","title":"Can LLMs Convert Graphs to Text-Attributed Graphs?","created":"2024-12-13","cited_by_count":19,"area":null},{"id":"2409.06446","title":"HexaCoder: Secure Code Generation via Oracle-Guided Synthetic Training Data","created":"2024-09-10","cited_by_count":16,"area":null},{"id":"2412.13169","title":"Algorithmic Fidelity of Large Language Models in Generating Synthetic German Public Opinions: A Case Study","created":"2024-12-17","cited_by_count":14,"area":null},{"id":"2502.04362","title":"LLMs can be easily Confused by Instructional Distractions","created":"2025-02-05","cited_by_count":13,"area":null},{"id":"2410.03083","title":"Scaling Parameter-Constrained Language Models with Quality Data","created":"2024-10-04","cited_by_count":12,"area":null},{"id":"2502.08924","title":"Escaping Collapse: The Strength of Weak Data for Large Language Model Training","created":"2025-02-13","cited_by_count":11,"area":null},{"id":"2503.01900","title":"LLM-Empowered Class Imbalanced Graph Prompt Learning for Online Drug Trafficking Detection","created":"2025-02-28","cited_by_count":11,"area":null},{"id":"2509.08494","title":"HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistants","created":"2025-09-10","cited_by_count":11,"area":null},{"id":"2407.11784","title":"Data-Juicer Sandbox: A Feedback-Driven Suite for Multimodal Data-Model Co-development","created":"2024-07-16","cited_by_count":10,"area":null},{"id":"2506.03448","title":"RefEdit: A Benchmark and Method for Improving Instruction-based Image Editing Model on Referring Expressions","created":"2025-06-03","cited_by_count":10,"area":null},{"id":"2505.22830","title":"What Has Been Lost with Synthetic Evaluation?","created":"2025-05-28","cited_by_count":9,"area":null},{"id":"2510.25817","title":"A Survey on Efficient Large Language Model Training: From Data-centric Perspectives","created":"2025-10-29","cited_by_count":9,"area":null},{"id":"2601.17058","title":"Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMs","created":"2026-01-22","cited_by_count":9,"area":null},{"id":"2502.15419","title":"Beyond Translation: LLM-Based Data Generation for Multilingual Fact-Checking","created":"2025-02-21","cited_by_count":8,"area":null},{"id":"2502.01683","title":"LLM-Powered Benchmark Factory: Reliable, Generic, and Efficient","created":"2025-02-02","cited_by_count":7,"area":null},{"id":"2507.07229","title":"SynthTextEval: Synthetic Text Data Generation and Evaluation for High-Stakes Domains","created":"2025-07-09","cited_by_count":7,"area":null},{"id":"2502.05467","title":"Position: LLMs Can be Good Tutors in English Education","created":"2025-02-08","cited_by_count":6,"area":null},{"id":"2503.09956","title":"DeepSeek-Inspired Exploration of RL-based LLMs and Synergy with Wireless Networks: A Survey","created":"2025-03-13","cited_by_count":6,"area":null},{"id":"2509.08653","title":"Generative Data Refinement: Just Ask for Better Data","created":"2025-09-10","cited_by_count":6,"area":null},{"id":"2409.07489","title":"RAGent: Retrieval-based Access Control Policy Generation","created":"2024-09-08","cited_by_count":5,"area":null},{"id":"2410.05021","title":"DEPT: Decoupled Embeddings for Pre-training Language Models","created":"2024-10-07","cited_by_count":5,"area":null},{"id":"2411.10163","title":"Compound-QA: A Benchmark for Evaluating LLMs on Compound Questions","created":"2024-11-15","cited_by_count":5,"area":null},{"id":"2506.20274","title":"Enterprise Large Language Model Evaluation Benchmark","created":"2025-06-25","cited_by_count":5,"area":null},{"id":"2507.06968","title":"Scaling Towards the Information Boundary of Instruction Sets: The Infinity Instruct Subject Technical Report","created":"2025-07-09","cited_by_count":5,"area":null},{"id":"2412.09807","title":"LLM Distillation for Efficient Few-Shot Multiple Choice Question Answering","created":"2024-12-13","cited_by_count":4,"area":null},{"id":"2502.00322","title":"MODS: Moderating a Mixture of Document Speakers to Summarize Debatable Queries in Document Collections","created":"2025-02-01","cited_by_count":4,"area":null},{"id":"2502.11533","title":"Be Cautious When Merging Unfamiliar LLMs: A Phishing Model Capable of Stealing Privacy","created":"2025-02-17","cited_by_count":4,"area":null},{"id":"2504.00513","title":"Leveraging LLMs for User Stories in AI Systems: UStAI Dataset","created":"2025-04-01","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":"2508.01556","title":"Empowering Tabular Data Preparation with Language Models: Why and How?","created":"2025-08-03","cited_by_count":4,"area":null},{"id":"2601.09692","title":"Routing with Generated Data: Annotation-Free LLM Skill Estimation and Expert Selection","created":"2026-01-14","cited_by_count":4,"area":null},{"id":"2409.07088","title":"Ontology-Free General-Domain Knowledge Graph-to-Text Generation Dataset Synthesis using Large Language Model","created":"2024-09-11","cited_by_count":3,"area":null},{"id":"2410.12499","title":"With a Grain of SALT: Are LLMs Fair Across Social Dimensions?","created":"2024-10-16","cited_by_count":3,"area":null},{"id":"2412.03824","title":"Towards Data Governance of Frontier AI Models","created":"2024-12-05","cited_by_count":3,"area":null},{"id":"2412.09247","title":"Make Satire Boring Again: Reducing Stylistic Bias of Satirical Corpus by Utilizing Generative LLMs","created":"2024-12-12","cited_by_count":3,"area":null},{"id":"2503.10838","title":"Who Relies More on World Knowledge and Bias for Syntactic Ambiguity Resolution: Humans or LLMs?","created":"2025-03-13","cited_by_count":3,"area":null},{"id":"2504.13217","title":"Sustainability via LLM Right-sizing","created":"2025-04-17","cited_by_count":3,"area":null},{"id":"2504.16188","title":"FinNLI: Novel Dataset for Multi-Genre Financial Natural Language Inference Benchmarking","created":"2025-04-22","cited_by_count":3,"area":null},{"id":"2506.23610","title":"Evaluating the Simulation of Human Personality-Driven Susceptibility to Misinformation with LLMs","created":"2025-06-30","cited_by_count":3,"area":null},{"id":"2509.14405","title":"Adding LLMs to the psycholinguistic norming toolbox: A practical guide to getting the most out of human ratings","created":"2025-09-17","cited_by_count":3,"area":null},{"id":"2509.18181","title":"Synthesizing Attitudes, Predicting Actions (SAPA): Behavioral Theory-Guided LLMs for Ridesourcing Mode Choice Modeling","created":"2025-09-18","cited_by_count":3,"area":null},{"id":"2510.18250","title":"ssToken: Self-modulated and Semantic-aware Token Selection for LLM Fine-tuning","created":"2025-10-21","cited_by_count":3,"area":null},{"id":"2511.04473","title":"Ground-Truth Subgraphs for Better Training and Evaluation of Knowledge Graph Augmented LLMs","created":"2025-11-06","cited_by_count":3,"area":null},{"id":"2512.14562","title":"Polypersona: Persona-Grounded LLM for Synthetic Survey Responses","created":"2025-12-16","cited_by_count":3,"area":null},{"id":"2602.10074","title":"CAPID: Context-Aware PII Detection for Question-Answering Systems","created":"2026-02-10","cited_by_count":3,"area":null},{"id":"2501.17980","title":"Limits to AI Growth: The Ecological and Social Consequences of Scaling","created":"2025-01-29","cited_by_count":2,"area":null},{"id":"2504.17355","title":"Collaborative Multi-Agent Reinforcement Learning for Automated Feature Transformation with Graph-Driven Path Optimization","created":"2025-04-24","cited_by_count":2,"area":null},{"id":"2504.20605","title":"TF1-EN-3M: Three Million Synthetic Moral Fables for Training Small, Open Language Models","created":"2025-04-29","cited_by_count":2,"area":null},{"id":"2505.23996","title":"Is Your Model Fairly Certain? Uncertainty-Aware Fairness Evaluation for LLMs","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2506.04172","title":"Does Prompt Design Impact Quality of Data Imputation by LLMs?","created":"2025-06-04","cited_by_count":2,"area":null},{"id":"2507.05750","title":"DocTalk: Scalable Graph-based Dialogue Synthesis for Enhancing LLM Conversational Capabilities","created":"2025-07-08","cited_by_count":2,"area":null},{"id":"2509.07829","title":"Building Large-Scale English-Romanian Literary Translation Resources with Open Models","created":"2025-09-09","cited_by_count":2,"area":null},{"id":"2509.19770","title":"EnAnchored-X2X: English-Anchored Optimization for Many-to-Many Translation","created":"2025-09-24","cited_by_count":2,"area":null},{"id":"2510.11218","title":"The Curious Case of Factual (Mis)Alignment between LLMs' Short- and Long-Form Answers","created":"2025-10-13","cited_by_count":2,"area":null},{"id":"2512.07246","title":"Ensembling LLM-Induced Decision Trees for Explainable and Robust Error Detection","created":"2025-12-08","cited_by_count":2,"area":null},{"id":"2601.06225","title":"Classroom AI: Large Language Models as Grade-Specific Teachers","created":"2026-01-09","cited_by_count":2,"area":null},{"id":"2605.06901","title":"Reflections and New Directions for Human-Centered Large Language Models","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2605.30637","title":"EHRBench: An Automated and Reliable EHR-based Benchmark for Clinical Decision Making with LLMs","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2608.22236","title":"MRMAD: A Multi-Round Multi-Audio Benchmark for Evaluating Acoustic Degradation Perception in Large Audio-Language Models","created":"2026-08-23","cited_by_count":2,"area":null},{"id":"2407.14371","title":"Open Artificial Knowledge","created":"2024-07-19","cited_by_count":1,"area":null},{"id":"2502.10577","title":"Man Made Language Models? Evaluating LLMs' Perpetuation of Masculine Generics Bias","created":"2025-02-14","cited_by_count":1,"area":null},{"id":"2504.10167","title":"C-FAITH: A Chinese Fine-Grained Benchmark for Automated Hallucination Evaluation","created":"2025-04-14","cited_by_count":1,"area":null},{"id":"2505.03025","title":"A Typology of Synthetic Datasets for Dialogue Processing in Clinical Contexts","created":"2025-05-05","cited_by_count":1,"area":null},{"id":"2505.03265","title":"Synthline: A Product Line Approach for Synthetic Requirements Engineering Data Generation using Large Language Models","created":"2025-05-06","cited_by_count":1,"area":null},{"id":"2505.11010","title":"ReviewInstruct: A Review-Driven Multi-Turn Conversations Generation Method for Large Language Models","created":"2025-05-16","cited_by_count":1,"area":null},{"id":"2505.20500","title":"Beyond Keywords: Evaluating Large Language Model Classification of Nuanced Ableism","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2505.22777","title":"MEDAL: A Framework for Benchmarking LLMs as Multilingual Open-Domain Dialogue Evaluators","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2507.23440","title":"Self-Foveate: Enhancing Diversity and Difficulty of Synthesized Instructions from Unsupervised Text via Multi-Level Foveation","created":"2025-07-31","cited_by_count":1,"area":null},{"id":"2508.00385","title":"Multi-Layer Attention is the Amplifier of Demonstration Effectiveness","created":"2025-08-01","cited_by_count":1,"area":null},{"id":"2508.19069","title":"Can Structured Templates Facilitate LLMs in Tackling Harder Tasks? : An Exploration of Scaling Laws by Difficulty","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2510.13884","title":"Too Open for Opinion? Embracing Open-Endedness in Large Language Models for Social Simulation","created":"2025-10-14","cited_by_count":1,"area":null},{"id":"2512.18682","title":"Solver-Independent Automated Problem Formulation via LLMs for High-Cost Simulation-Driven Design","created":"2025-12-21","cited_by_count":1,"area":null},{"id":"2512.22603","title":"Structured Prompting and LLM Ensembling for Multimodal Conversational Aspect-based Sentiment Analysis","created":"2025-12-27","cited_by_count":1,"area":null},{"id":"2601.11575","title":"Concept Attractors in LLMs and their Applications","created":"2025-12-30","cited_by_count":1,"area":null},{"id":"2603.03322","title":"Can Large Language Models Derive New Knowledge? A Dynamic Benchmark for Biological Knowledge Discovery","created":"2026-02-10","cited_by_count":1,"area":null},{"id":"2604.17803","title":"Adversarial Arena: Crowdsourcing Data Generation through Interactive Competition","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2604.17894","title":"Automatic Slide Updating with User-Defined Dynamic Templates and Natural Language Instructions","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2606.30312","title":"DialogPII: A multilingual dataset of synthetic dialog transcripts to detect personal information","created":"2026-06-29","cited_by_count":1,"area":null},{"id":"2608.30023","title":"Demand-Side Measurement for Generative Engine Optimization: Constructing and Validating a Million-Persona, Intent-Annotated Buyer Corpus","created":"2026-08-30","cited_by_count":1,"area":null},{"id":"2410.12046","title":"Towards Realistic Evaluation of Commit Message Generation by Matching Online and Offline Settings","created":"2024-10-15","cited_by_count":0,"area":null},{"id":"2412.20057","title":"\"My life is miserable, have to sign 500 autographs everyday\": Exposing Humblebragging, the Brags in Disguise","created":"2024-12-28","cited_by_count":0,"area":null},{"id":"2503.11046","title":"Measuring Similarity in Causal Graphs: A Framework for Semantic and Structural Analysis","created":"2025-03-14","cited_by_count":0,"area":null},{"id":"2503.24206","title":"Synthetic News Generation for Fake News Classification","created":"2025-03-31","cited_by_count":0,"area":null},{"id":"2505.17615","title":"Large language model as user daily behavior data generator: balancing population diversity and individual personality","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2506.00986","title":"Talking to Data: Designing Smart Assistants for Humanities Databases","created":"2025-06-01","cited_by_count":0,"area":null},{"id":"2506.17264","title":"OAT-Rephrase: Optimization-Aware Training Data Rephrasing for Zeroth-Order LLM Fine-Tuning","created":"2025-06-10","cited_by_count":0,"area":null},{"id":"2506.22491","title":"PromptAug: Fine-grained Conflict Classification Using Data Augmentation","created":"2025-06-24","cited_by_count":0,"area":null},{"id":"2506.22515","title":"In-context learning for the classification of manipulation techniques in phishing emails","created":"2025-06-26","cited_by_count":0,"area":null}],"next_cursor":"100"}