埋め込み次元の増大が単純ソートタスクにおける世界モデルを強化する
Higher Embedding Dimension Creates a Stronger World Model for a Simple Sorting Task
強化学習でバブルソート風の隣接交換を学習するTransformerにおいて、埋め込み次元が内部世界モデルの形成に与える影響を調査し、次元が大きいほど構造的で解釈可能な表現が得られることを示した。
著者: Brady Bhalla, Honglu Fan, Nancy Chen, Tony Yue YU
分類: cs.LG, cs.AI
原文アブストラクト
We investigate how embedding dimension affects the emergence of an internal "world model" in a transformer trained with reinforcement learning to perform bubble-sort-style adjacent swaps. Models achieve high accuracy even with very small embedding dimensions, but larger dimensions yield more faithful, consistent, and robust internal representations. In particular, higher embedding dimensions strengthen the formation of structured internal representation and lead to better interpretability. After hundreds of experiments, we observe two consistent mechanisms: (1) the last row of the attention weight matrix monotonically encodes the global ordering of tokens; and (2) the selected transposition aligns with the largest adjacent difference of these encoded values. Our results provide quantitative evidence that transformers build structured internal world models and that model size improves representation quality in addition to end performance. We release our metrics and analyses, which can be used to probe similar algorithmic tasks.