{"total":15,"rows":[{"id":"2509.09009","title":"Open-sci-ref-0.01: open and reproducible reference baselines for language model and dataset comparison","created":"2025-09-10","cited_by_count":6,"area":null},{"id":"2508.02271","title":"Dynaword: From One-shot to Continuously Developed Datasets","created":"2025-08-04","cited_by_count":3,"area":null},{"id":"2606.00147","title":"RAFT: Data Refinement and Adaptive Distillation for Domain Fine-Tuning with Alleviated Forgetting","created":"2026-05-29","cited_by_count":3,"area":null},{"id":"2603.10002","title":"SpreadsheetArena: Decomposing Preference in LLM Generation of Spreadsheet Workbooks","created":"2026-02-16","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":"2606.03773","title":"KletterMix: Climbing Toward High-Quality German Pretraining Data - The Full Report","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2604.14053","title":"From Where Words Come: Efficient Regularization of Code Tokenizers Through Source Attribution","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2604.15460","title":"The Crutch or the Ceiling? How Different Generations of LLMs Shape EFL Student Writings","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2606.12114","title":"Detecting Sensitive Personal Information in Japanese Pre-Training Corpora for Large Language Models","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2606.28867","title":"Open but Incompatible: A License Compatibility Analysis of Corpora for Low-Resource African Languages","created":"2026-06-27","cited_by_count":0,"area":null},{"id":"2608.12278","title":"Structural Silence: When AI Infrastructure Fails Speakers of Underrepresented Languages","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2608.30609","title":"Reading the News: Adapting Large Language Models to Swedish Journalism Through Continued Pre-Training","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.22208","title":"Replicating the Geometry of Emotion Representations in a Base Open-Weights Model","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.37891","title":"It's All Training: A Fully Synthetic Single-Stage Recipe for LLMs","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.02092","title":"Scalable, Transferable Meta-network for Data Selection Requires a Different Loss (and Why the Obvious Choice is Problematic)","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}