TPAW uses teams of current and historical model checkpoints that collaborate and compete, plus adaptive weightings for responses and players, to improve self-supervised LLM alignment and outperform baselines.
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (ACL) , pages=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Team-Based Self-Play With Dual Adaptive Weighting for Fine-Tuning LLMs
TPAW uses teams of current and historical model checkpoints that collaborate and compete, plus adaptive weightings for responses and players, to improve self-supervised LLM alignment and outperform baselines.