{"total":18,"rows":[{"id":"2509.14234","title":"Compute as Teacher: Turning Inference Compute Into Reference-Free Supervision","created":"2025-09-17","cited_by_count":18,"area":null},{"id":"2410.23463","title":"MDCure: A Scalable Pipeline for Multi-Document Instruction-Following","created":"2024-10-30","cited_by_count":10,"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":"2501.09368","title":"Aligning Instruction Tuning with Pre-training","created":"2025-01-16","cited_by_count":7,"area":null},{"id":"2503.17195","title":"TreeSynth: Synthesizing Diverse Data from Scratch via Tree-Guided Subspace Partitioning","created":"2025-03-21","cited_by_count":7,"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":"2411.10163","title":"Compound-QA: A Benchmark for Evaluating LLMs on Compound Questions","created":"2024-11-15","cited_by_count":5,"area":null},{"id":"2607.28109","title":"Beyond Rephrasing: Book-Level Organization Improves Synthetic Textbook Data for Mid-Training","created":"2026-07-30","cited_by_count":3,"area":null},{"id":"2505.15087","title":"HopWeaver: Cross-Document Synthesis of High-Quality and Authentic Multi-Hop Questions","created":"2025-05-21","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":"2508.07087","title":"SQL-Exchange: Transforming SQL Queries Across Domains","created":"2025-08-09","cited_by_count":1,"area":null},{"id":"2508.10013","title":"Semantic Bridge: Universal Multi-Hop Question Generation via AMR-Driven Graph Synthesis","created":"2025-08-06","cited_by_count":1,"area":null},{"id":"2508.04278","title":"Large Language Model's Multi-Capability Alignment in Biomedical Domain","created":"2025-08-06","cited_by_count":0,"area":null},{"id":"2602.17465","title":"Entropy-Based Data Selection for Language Models","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2605.25835","title":"Context-Instrumental Data Distillation for Kubernetes Manifest Generation: Method and Experimental Evaluation","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2606.30175","title":"CORTEX: High-Quality Cross-Domain Organization of Web-Scale Corpora through Ontological Corpus Graph","created":"2026-06-29","cited_by_count":0,"area":null},{"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":"2610.03625","title":"FALCON: A Model and Dataset Agnostic Framework for Synthetic Data Generation for NL2SQL Pairs","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}