{"total":61,"rows":[{"id":"2508.03682","title":"Self-Questioning Language Models","created":"2025-08-05","cited_by_count":50,"area":null},{"id":"2603.10055","title":"Training Language Models via Neural Cellular Automata","created":"2026-03-09","cited_by_count":15,"area":null},{"id":"2505.14423","title":"Scaling Low-Resource MT via Synthetic Data Generation with LLMs","created":"2025-05-20","cited_by_count":14,"area":"synth"},{"id":"2509.03059","title":"Loong: Synthesize Long Chain-of-Thoughts at Scale through Verifiers","created":"2025-09-03","cited_by_count":14,"area":"lr"},{"id":"2510.19771","title":"Beyond Reactivity: Measuring Proactive Problem Solving in LLM Agents","created":"2025-10-22","cited_by_count":10,"area":"agents"},{"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":"2509.24506","title":"Building Benchmarks from the Ground Up: Community-Centered Evaluation of LLMs in Healthcare Chatbot Settings","created":"2025-09-29","cited_by_count":5,"area":null},{"id":"2510.02330","title":"EntropyLong: Effective Long-Context Training via Predictive Uncertainty","created":"2025-09-26","cited_by_count":5,"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":"2507.07852","title":"Pre-Trained AI Model Assisted Online Decision-Making under Missing Covariates: A Theoretical Perspective","created":"2025-07-10","cited_by_count":3,"area":null},{"id":"2509.21479","title":"Filtering with Confidence: When Data Augmentation Meets Conformal Prediction","created":"2025-09-25","cited_by_count":3,"area":null},{"id":"2602.03183","title":"Privasis: Synthesizing the Largest \"Public\" Private Dataset from Scratch","created":"2026-02-03","cited_by_count":3,"area":null},{"id":"2602.12172","title":"Pedagogically-Inspired Data Synthesis for Language Model Knowledge Distillation","created":"2026-02-12","cited_by_count":3,"area":"synth"},{"id":"2605.01248","title":"$S^3$-R1: Learning to Retrieve and Answer Step-by-Step with Synthetic Data","created":"2026-05-02","cited_by_count":3,"area":"lr"},{"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":"2506.04172","title":"Does Prompt Design Impact Quality of Data Imputation by LLMs?","created":"2025-06-04","cited_by_count":2,"area":null},{"id":"2508.01317","title":"LinkQA: Synthesizing Diverse QA from Multiple Seeds Strongly Linked by Knowledge Points","created":"2025-08-02","cited_by_count":2,"area":null},{"id":"2508.19570","title":"Generative Models for Synthetic Data: Transforming Data Mining in the GenAI Era","created":"2025-08-27","cited_by_count":2,"area":"diffusion"},{"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":"2511.03928","title":"SynQuE: Estimating Synthetic Dataset Quality Without Annotations","created":"2025-11-06","cited_by_count":2,"area":"synth"},{"id":"2511.10338","title":"BhashaKritika: Building Synthetic Pretraining Data at Scale for Indic Languages","created":"2025-11-13","cited_by_count":2,"area":"synth"},{"id":"2602.05648","title":"Modelling the Morphology of Verbal Paradigms: A Case Study in the Tokenization of Turkish and Hebrew","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2603.00059","title":"Stochastic Parrots or Singing in Harmony? Testing Five Leading LLMs for their Ability to Replicate a Human Survey with Synthetic Data","created":"2026-02-10","cited_by_count":2,"area":"synth"},{"id":"2603.02239","title":"Engineering Reasoning and Instruction (ERI) Benchmark: A Large Taxonomy-driven Dataset for Foundation Models and Agents","created":"2026-02-16","cited_by_count":2,"area":"lr"},{"id":"2603.10243","title":"GR-SAP: Generative Replay for Safety Alignment Preservation during Fine-Tuning","created":"2026-03-10","cited_by_count":2,"area":"alignment"},{"id":"2604.22313","title":"CLARITY: A Framework and Benchmark for Conversational Language Ambiguity and Unanswerability in Interactive NL2SQL Systems","created":"2026-04-24","cited_by_count":2,"area":null},{"id":"2608.24065","title":"Mechanistic Circuit Identification for Controllable Data Generation","created":"2026-08-25","cited_by_count":2,"area":null},{"id":"2503.15133","title":"EmoGRACE: Aspect-based emotion analysis for social media data","created":"2025-03-19","cited_by_count":1,"area":null},{"id":"2505.14425","title":"From Templates to Natural Language: Generalization Challenges in Instruction-Tuned LLMs for Spatial Reasoning","created":"2025-05-20","cited_by_count":1,"area":"lr"},{"id":"2508.07087","title":"SQL-Exchange: Transforming SQL Queries Across Domains","created":"2025-08-09","cited_by_count":1,"area":null},{"id":"2509.20837","title":"Verification Limits Code LLM Training","created":"2025-09-25","cited_by_count":1,"area":null},{"id":"2510.17928","title":"EvoSyn: Generalizable Evolutionary Data Synthesis for Verifiable Learning","created":"2025-10-20","cited_by_count":1,"area":"agents"},{"id":"2510.21970","title":"Performance Trade-offs of Optimizing Small Language Models for E-Commerce","created":"2025-10-24","cited_by_count":1,"area":null},{"id":"2510.26095","title":"ORBIT -- Open Recommendation Benchmark for Reproducible Research with Hidden Tests","created":"2025-10-30","cited_by_count":1,"area":null},{"id":"2601.17230","title":"CaseFacts: A Benchmark for Legal Fact-Checking and Precedent Retrieval","created":"2026-01-23","cited_by_count":1,"area":null},{"id":"2602.20799","title":"Unseen-Codebases-Domain Data Synthesis and Training Based on Code Graphs","created":"2026-02-24","cited_by_count":1,"area":"synth"},{"id":"2604.17803","title":"Adversarial Arena: Crowdsourcing Data Generation through Interactive Competition","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2605.05267","title":"Bridging Generation and Training: A Systematic Review of Quality Issues in LLMs for Code","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2605.26872","title":"When the Strongest Teacher Is Not the Best Teacher: Student-Centric Answer Selection","created":"2026-05-26","cited_by_count":1,"area":"lr"},{"id":"2607.16204","title":"Masked Diffusion Language Models are Strong and Steerable Text-Based World Models for Agentic RL","created":"2026-05-07","cited_by_count":1,"area":"wm"},{"id":"2510.03743","title":"APIDA-Chat: Structured Synthesis of API Search Dialogues to Bootstrap Conversational Agents","created":"2025-10-04","cited_by_count":0,"area":"agents"},{"id":"2510.07177","title":"CARPAS: Towards Content-Aware Refinement of Provided Aspects for Summarization in Large Language Models","created":"2025-10-08","cited_by_count":0,"area":null},{"id":"2601.03435","title":"The Critical Role of Aspects in Measuring Document Similarity","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2601.10410","title":"TF3-RO-50M: Training Compact Romanian Language Models from Scratch on Synthetic Moral Microfiction","created":"2026-01-15","cited_by_count":0,"area":null},{"id":"2601.21469","title":"Adaptive Confidence Gating in Multi-Agent Collaboration for Efficient and Optimized Code Generation","created":"2026-01-29","cited_by_count":0,"area":"lr"},{"id":"2602.03119","title":"Function-Space Empirical Bayes Regularisation with Large Vision-Language Model Priors","created":"2026-02-03","cited_by_count":0,"area":"mllm"},{"id":"2602.04388","title":"On the use of LLMs to generate a dataset of Neural Networks","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2602.17778","title":"Asking Forever: Universal Activations Behind Turn Amplification in Conversational LLMs","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2602.23312","title":"Evaluating Zero-Shot and One-Shot Adaptation of Small Language Models in Leader-Follower Interaction","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2603.13625","title":"Design and evaluation of an agentic workflow for crisis-related synthetic tweet datasets","created":"2026-03-13","cited_by_count":0,"area":"agents"},{"id":"2603.25227","title":"Comparing Natural and Synthetic Structured Data: A Study of the Passive Verb Alternation in French and Italian","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2604.24544","title":"STELLAR-E: a Synthetic, Tailored, End-to-end LLM Application Rigorous Evaluator","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2604.26986","title":"BatteryPass-12K: The First Dataset for the Novel Digital Battery Passport Conformance Task","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2605.14062","title":"Know When To Fold 'Em: Token-Efficient LLM Synthetic Data Generation via Multi-Stage In-Flight Rejection","created":"2026-05-13","cited_by_count":0,"area":"synth"},{"id":"2608.22894","title":"AraDetox: A Multi-Dialect Arabic Detoxification Dataset","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2608.29206","title":"Benevolent Bias in Multi-Turn Human-Agent Dialogue","created":"2026-08-29","cited_by_count":0,"area":"agents"},{"id":"2609.22164","title":"A Multi-Agent Pipeline for Source-Grounded Synthetic Note Generation from Longitudinal Structured EHR","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.25040","title":"BananaVLM: A Domain-Adapted Vision Language Model for Banana Crop Disease Diagnosis","created":"2026-08-27","cited_by_count":0,"area":"mllm"},{"id":"2609.38799","title":"Overlap, Unique and Conflict: Can LLMs Extract What They Can Recognize?","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.00779","title":"Effective Synthetic Data Curation Requires Group-Level Signals","created":"2026-09-30","cited_by_count":0,"area":"synth"},{"id":"2610.00928","title":"Efficient Task Adaptation in Large Language Models: A Survey of Weight-Based, Prompt-Based, and Embedding-Based Adaptations","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}