This paper considers multilingual pretraining as a cooperative game in which each language acts as a player that jointly contributes to pretraining, gaining the resulting reduction in test loss as the payoff and proposes a game-theoretic multilingual scaling law called ShapleyLaw.
Three findings emerge: joint depth-complexity coverage outperforms single-axis recipes; reasoning families respond non-uniformly, with abductive reasoning degrading outside the RL-covered region and task correlations clustering into deductive-abductive and inductive-analogy pairs; and uniform mixing outperforms staged...
It is shown that a lightweight LLM-only DPO update on tiny single-object-pair synthetic data mitigates the bias, lifting four-way robust accuracy by up to 100 points on synthetic data, and by 68.1 points on broader evaluation datasets WhatsUp, SpatialMQA-Direct, and VSR.
An adaptive threshold selection policy that chooses thresholds on validation data using pseudo-label precision and sample count is introduced and is combined with confidence-aware verifier training to support confidence-based selection of pseudo-labeled subsets.
Keizo Kato, Chen-Hui Chu, Yugo Murawaki et al.· Frontiers in Artificial Inte...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
