method · first seen 13 Nov 2026
self-play fine-tuning
Also: SPIN
Fine-tuning a model by having it generate synthetic samples that a discriminator separates from real data, iterating to align distributions.
Mentions per week
PapersCodeDiscussion
Earliest sources
- f-Divergence Self-Play for Tabular Anomaly Detection via Large Language ModelsPapers · 13 Nov 2026 · Hoang Tran Vuong, Linh Ngo Van, Dang Nguyen, Thin Nguyen, Phuoc Nguyen, Mehrtash…
Latest sources
- f-Divergence Self-Play for Tabular Anomaly Detection via Large Language ModelsPapers · 13 Nov 2026 · Hoang Tran Vuong, Linh Ngo Van, Dang Nguyen, Thin Nguyen, Phuoc Nguyen, Mehrtash…