AlignmentAlice
AltTrain: Can Reasoning Structure Be Aligned With Only 1,000 Examples?
Reasoning Structure Matters for Safety Alignment of Reasoning Models
Published: 12 May 2026 · Updated: 13 July 2026
Read the original sourceWhat the paper says
AltTrain argues that harmful responses in reasoning models come partly from the structure of their reasoning. It uses a lightweight supervised fine-tuning set to alter that structure without complex reinforcement learning.
The Critique
The premise is plausible: how a model reasons can matter as much as what it finally says. But 1,000 examples is a thin bridge to general safety. If the training set encodes a narrow safety pattern, the model may learn a template rather than a principle. The paper also needs to show that altered structure does not quietly reduce useful reasoning flexibility.
Why It Matters
If supervised structure editing works, it could make alignment cheaper. If it overfits, it becomes another brittle safety wrapper.
What They Missed
Hard capability-retention tests, multilingual safety cases, ambiguous dual-use prompts, and comparisons with RL-based methods under the same compute budget.
The Big Question
Is AltTrain changing the model's safety reasoning, or teaching it a safer-looking script?