AIarXiv
Ranked by formulaVerdict: NotableTraceForge: Distilling with Your Own Thinking
Using an LLM to generate training data for another is among the most general ways to train one, and it remains common practice.
Caveats
- Preprint; not yet peer reviewed.
VerdictWorth a reader's time today.
Abstract
Using an LLM to generate training data for another is among the most general ways to train one, and it remains common practice. Some frontier teams have closed that route for their own models: what comes back is an answer, or a short summary, without the detailed reasoning trace behind it. That is a little ironic: they were themselves built on distilling human knowledge, and distilling an open-source model is still entirely routine; the restriction applies to their own outputs alone. Recent work recovers the hidden reasoning by replaying encrypted blocks across models. It somehow works, but it breaks the providers' terms of service, so it is not something a product can be built on long-term. We built the alternative. We take the context and the teacher's answer as input, and generate the reasoning trace ourselves, in the style of the student's own model family. Training is two-stage, supervised and then adversarial: a generator learns to regenerate the family's own reasoning traces from their context and answer, and a critic learns how real a reasoning trace looks. Applied to a teacher's answer, the generator writes one in the family's style. An independent judge rates how likely traces are to be genuine on a scale from 0 to 1: ours average 0.68, real traces 0.66, and traces selected by the critic from four candidates 0.82. These are authenticity scores, not correctness rates. We test the idea on five benchmarks with everything else held fixed. On general tasks the five training corpora are about the same; on coding, the generated reasoning beats Fable 5's own thinking content. With the same 5,000 questions and the same teacher answers, HumanEval+ improves by 3.7 points and MBPP+ by 7.1 at the final checkpoint, and the MBPP+ lead holds at every checkpoint. We suspect that reasoning written in the student's family style is easier for it to learn from.
The editor's rubric
- Leverage3 / 5
- A method or resource many groups across the field will adopt within a year.
- Magnitude3 / 5
- Large gain: roughly 2x, or a clear new state of the art on a hard, unsaturated problem.
- Evidence3 / 5
- Solid: multiple benchmarks or cohorts, ablations, fair baselines, released code or data.
- Novelty2 / 5
- A new combination of known ideas.
- Trajectory3 / 5
- A clear path to scale.
- Stakes2 / 5
- Benefits a professional community (practitioners, clinicians, engineers).
Editor’s rationale
Heuristic triage from title and abstract text only, not a reading of the paper. Cues found: breadth (many tasks); gains (relative gain, outperforms); verification (multiple benchmarks, independent replication, code released); scale (scalable); stakes (general AI).
How the score was computed
Desks place stronger verdicts first, then use this score to order work within the same verdict.
- Merit
- 5.5 / 10
- Adjusted merit
- 4.7 / 10
- Attention
- 43%
- Freshness
- 75%
- Hugging Face upvotes16 (reference 25, via hf-daily, Oct 22, 2026, 13:43 UTC)