Is Convergence Inevitable? Tracing Output Homogeneity Back to Base Models

Excerpt

arXiv:2608.11426v2 Announce Type: replace Abstract: The lack of diversity in LM content is widely attributed to the alignment process, but how and where exactly in the pipeline this collapse begins is unknown. We argue that output homogeneity is likely learned during the pretraining phase, and only revealed or magnified during the alignment process. Specifically, we find that semantic convergence is observed from the first alignment stage--the instruction-tuning phase (SFT)--suggesting that homo