Training away its own bad reasoning lifts Qwen3-4B math scores by 7.5 points
imjustnewatai · x · 2026-09-13
A September 10 preprint takes an counterintuitive approach: instead of imitating an answer-fed teacher, it prompts a Qwen copy to reason carelessly, then trains the model away from those amplified patterns — with correct answers removed from training data. On Qwen3-4B, average accuracy across 7 math benchmarks rose 7.5 points vs just 1.0 from the teacher-based method; with thinking enabled the new method still gained 3 points. The author highlights the self-feedback loop: a model can generate useful improvement signals without knowing the correct solution.
More from Research
- AIR: Effective-Learning-Rate Scheduler Beats Cosine on 128B-Token MoE Pretraining — stochasticchasm · 2026-10-30
- CMU's Gym-Anything Auto-Builds 200+ Agent Environments from Any Software, Selected by GDP — wellecks · 2026-10-30
- NVIDIA researcher: train robot policies with privileged sim info, improving Pi 0.5 — wellecks · 2026-10-30
- Leveraging Simulator Privileged Information: Three Methods to Improve Robot Models — wellecks · 2026-10-30
- CMU Auto-Builds 25 Robot Simulations with Agents; Frontier Model Solves 0 of 25 Test Tasks — wellecks · 2026-10-30
- DeepMind's f_charton shares his take on the current state of AI and mathematics in Sorbonne talk — f_charton · 2026-10-30