Comparison of techniques for fine-tuning open-weight models for entity extraction from radiology reports
Fine-tuned Gemma-3-12B matches GPT-4o on hemorrhage extraction when distilled from real reports.
48
AI model
Gemma-3-12B
- Mentions · 7d0
- Mentions · 30d0
- All mentions2
- First seenSep 26, 2026
- Last mentionedSep 30, 2026
Timeline
2 articles · newest firstThe Decomposition Tax: LLM Pipelines Lose Up to 40 Accuracy Points at Their Own Interfaces
LLM pipelines lose up to 40.5 accuracy points at stage interfaces; re-grounding after the loss helps.
52
Appears with
- GPT-4oai model · 1
- OpenAIvendor · 1
- Googlevendor · 1
- Gemma-4-12Bai model · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.