PulseAugur
EN
LIVE 16:37:40

Nous Research cuts Qwen propaganda output by 95% in fine-tuning

By PulseAugur Editorial · [1 sources] ·

Nous Research has fine-tuned Alibaba's Qwen model, significantly reducing instances of propaganda generation. After training on 53 million tokens, the model's propaganda output decreased from 22% to 0.9%. Nous Research suggests this demonstrates that alignment in open-source models can be more easily altered than previously thought, though independent verification of these findings is still pending. AI

IMPACT Demonstrates a method for reducing propaganda in open-source models, potentially improving safety and trustworthiness.

RANK_REASON The item describes a fine-tuning effort on an existing model and its results, which falls under research. [lever_c_demoted from research: ic=1 ai=1.0]

Read on Mastodon — mastodon.social →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Nous Research cuts Qwen propaganda output by 95% in fine-tuning

How we ranked this

Signal score
4 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
The item describes a fine-tuning effort on an existing model and its results, which falls under research. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
model release, safety
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. Mastodon — mastodon.social TIER_1 English(EN) · schuler ·

    Nous Research fine-tuned Alibaba's Qwen model on 53 million tokens and reports propaganda answers dropped from 22% to 0.9%. The lab argues this shows alignment

    Nous Research fine-tuned Alibaba's Qwen model on 53 million tokens and reports propaganda answers dropped from 22% to 0.9%. The lab argues this shows alignment in open models may be easier to override than assumed. What remains unclear: how the findings hold up under independent …

    LINKS implicator.ai/nous-research-unveils-arete…

RELATED ENTITIES

RELATED TOPICS