hotai.news
← Back to AI Newsflash
AI Briefings / Content Guide
AIHOT · Published November 8, 2026 at 12:45

Nous Research releases Arete-27B, reducing Qwen3.8-27B's promotional responses from 22% to 0.9%

AI Brief

Nous Research releases Arete-27B, a pure supervised fine-tune of Qwen3.8-27B. In its own evaluation set of 803 prompts, the proportion of responses containing promotional content drops from 22% to 0.9%, while factual accuracy scores rise from 2.32 to 2.98.

Return to original text

A short introduction is retained here; the full text from the source website is not reposted. For specific wording and subsequent updates, please refer to the original article.

Open AIHOT original