Small LLMs fail complement consistency in agent opinion simulations
Paired true and false reports from Qwen3-4B, Llama-3.2-3B and Gemma-3-4B do not sum to one, and complementary populations diverge within five rounds.
36
AI model
Gemma-3-4B
- Mentions · 7d1
- Mentions · 30d2
- All mentions2
- First seenSep 27, 2026
- Last mentioned2d ago
Timeline
2 articles · newest firstPersona Dosing: Calibrated Activation Steering for Graded Trait Control
PersonaDose calibrates activation steering so models express requested persona intensities.
46
Appears with
- Qwen3-8Bai model · 1
- Llama-3.2-3Bai model · 1
- Llama-3.1-8Bai model · 1
- Qwen3-4Bai 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.