{"total":24,"rows":[{"id":"2602.21193","title":"On Data Engineering for Scaling LLM Terminal Capabilities","created":"2026-02-24","cited_by_count":43,"area":null},{"id":"2412.13337","title":"Unveiling the Secret Recipe: A Guide For Supervised Fine-Tuning Small LLMs","created":"2024-12-17","cited_by_count":40,"area":null},{"id":"2511.09148","title":"LoopTool: Closing the Data-Training Loop for Robust LLM Tool Calls","created":"2025-11-12","cited_by_count":17,"area":null},{"id":"2505.13772","title":"Krikri: Advancing Open Large Language Models for Greek","created":"2025-05-19","cited_by_count":14,"area":null},{"id":"2410.04524","title":"Toward Secure Tuning: Mitigating Security Risks from Instruction Fine-Tuning","created":"2024-10-06","cited_by_count":8,"area":null},{"id":"2601.15793","title":"HumanLLM: Towards Personalized Understanding and Simulation of Human Nature","created":"2026-01-22","cited_by_count":8,"area":null},{"id":"2412.17743","title":"YuLan-Mini: An Open Data-efficient Language Model","created":"2024-12-23","cited_by_count":7,"area":null},{"id":"2506.11117","title":"ScIRGen: Synthesize Realistic and Large-Scale RAG Dataset for Scientific Research","created":"2025-06-09","cited_by_count":7,"area":null},{"id":"2509.06795","title":"Anchoring Refusal Direction: Mitigating Safety Risks in Tuning via Projection Constraint","created":"2025-09-08","cited_by_count":7,"area":null},{"id":"2507.22080","title":"CodeEvo: Interaction-Driven Synthesis of Code-centric Data through Hybrid and Iterative Feedback","created":"2025-07-25","cited_by_count":5,"area":null},{"id":"2510.03777","title":"GuidedSampling: Steering LLMs Towards Diverse Candidate Solutions at Inference-Time","created":"2025-10-04","cited_by_count":5,"area":null},{"id":"2503.01493","title":"Sherkala-Chat: Building a State-of-the-Art LLM for Kazakh in a Moderately Resourced Setting","created":"2025-03-03","cited_by_count":4,"area":null},{"id":"2509.21294","title":"UPDESH: Synthesizing Grounded Instruction Tuning Data for 13 Indic Languages","created":"2025-09-25","cited_by_count":4,"area":null},{"id":"2601.09733","title":"Closing the Data Loop: Using OpenDataArena to Engineer Superior Training Datasets","created":"2025-12-30","cited_by_count":4,"area":null},{"id":"2606.31537","title":"DataEvolver: Self-Evolving Multi-Agent Data Construction for Text-Rich Image Generation","created":"2026-06-30","cited_by_count":3,"area":null},{"id":"2410.18146","title":"Meaning Typed Prompting: A Technique for Efficient, Reliable Structured Output Generation","created":"2024-10-22","cited_by_count":2,"area":null},{"id":"2504.14523","title":"Learning from Reasoning Failures via Synthetic Data Generation","created":"2025-04-20","cited_by_count":2,"area":null},{"id":"2505.18011","title":"Training with Pseudo-Code for Instruction Following","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2505.22157","title":"LASER: Stratified Selective Sampling for Instruction Tuning with Dedicated Scoring Strategy","created":"2025-05-28","cited_by_count":1,"area":null},{"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":"2601.22159","title":"RedSage: A Cybersecurity Generalist LLM","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2604.21637","title":"Multilinguality at the Edge: Developing Language Models for the Global South","created":"2026-04-23","cited_by_count":1,"area":null},{"id":"2602.20296","title":"Learning to Solve Complex Problems via Dataset Decomposition","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2610.12274","title":"HarnessSQL: Harness-Native Training for SQL Agents in Realistic Database Environments","created":"2026-10-08","cited_by_count":0,"area":null}],"next_cursor":null}