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=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
DEPO uses historical data to build a data-dependent uncertainty bonus for exploration in online RLHF, yielding an adaptive regret bound and stronger empirical performance than baselines.
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.
-
Data-dependent Exploration for Online Reinforcement Learning from Human Feedback
DEPO uses historical data to build a data-dependent uncertainty bonus for exploration in online RLHF, yielding an adaptive regret bound and stronger empirical performance than baselines.