pith:NGKYKIAK
Adaptive Teacher Exposure for Self-Distillation in LLM Reasoning
Adaptive control of how much reference reasoning the teacher sees during self-distillation improves LLM performance on math tasks.
arxiv:2605.11458 v2 · 2026-05-12 · cs.AI · cs.CL · cs.LO
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{NGKYKIAK2YNQHDSTDVY4WVD2XY}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
Experiments on AIME 24, AIME 25, and HMMT 25 across Qwen3-{1.7B, 4B, 8B} show that ATESD consistently outperforms competitive self-distillation and RL baselines, improving over OPSD by +0.95, +2.05, and +2.33 Average@12 points respectively.
That a lightweight Beta-policy controller, optimized via a discounted learning-progress reward on compact training-state statistics, will reliably produce exposure decisions that improve long-term student performance without introducing training instability or benchmark-specific overfitting.
ATESD makes teacher exposure to reference reasoning a learnable control variable via a Beta-policy optimized on future student improvement, yielding gains of up to +2.33 points over fixed-exposure self-distillation on AIME and HMMT math benchmarks.
Cited by
Receipt and verification
| First computed | 2026-05-28T01:04:42.194431Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
699585200ad61b038e531d71cb547abe2edccb32c3e145ebfe106541a40a44fd
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/NGKYKIAK2YNQHDSTDVY4WVD2XY \
| jq -c '.canonical_record' \
| python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 699585200ad61b038e531d71cb547abe2edccb32c3e145ebfe106541a40a44fd
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "904a1023c98c8cc7d93e5da3ce5481f1f93879c80f6c2466377bc5f15cb4ccb9",
"cross_cats_sorted": [
"cs.CL",
"cs.LO"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.AI",
"submitted_at": "2026-05-12T03:15:58Z",
"title_canon_sha256": "c6d1d4231c0b2deef372a95b664109c6d744977b41c04ca0d03397984278f7c7"
},
"schema_version": "1.0",
"source": {
"id": "2605.11458",
"kind": "arxiv",
"version": 2
}
}