A multilingual, multi-seed study finds that LLM pre-pretraining gains are highly dependent on setup and random seed, with consistent benefits confined to small models with the Llama tokenizer on 128-Dyck.
The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Instability of LLM Pre-Pretraining: It Doesn't Always Help. An Investigation on Multiple Languages
A multilingual, multi-seed study finds that LLM pre-pretraining gains are highly dependent on setup and random seed, with consistent benefits confined to small models with the Llama tokenizer on 128-Dyck.