# Preprint reports training gains from adjusting domain loss weights

_Published Monday, October 26, 2026 at 8:09 AM EDT · AI, Science · Latest · Tier 2 — Notable_

Researchers report that adjusting how strongly different training domains contribute to learning improved all five evaluated benchmarks for a 1.5B language model trained on 240B tokens. Their preprint reports an average gain of +7.84 percentage points over a matched direct mixture, including +17.06 on GSM8K and +9.00 on MATH.

The proposed LARE method automatically adjusts domain weights using running loss statistics while keeping the sampled data mixture unchanged. It changes the influence of training examples without adding domain exposure or requiring additional runs to search for weights. The reported benchmark results concern the evaluated 1.5B model.

## Sources

- [cs.AI updates on arXiv.org](https://arxiv.org/abs/2610.32141)

---
Canonical: https://techandbusiness.org/newswire/U0i0UDv_RujSXeFw3wC41m
Published: 2026-10-26T12:09:49.342Z
Story chronology: 2026-10-26T04:00:00.000Z
Retrieved: 2026-10-26T14:48:41.979Z
Publisher: Tech & Business (techandbusiness.org)