pith:7X2WC3QO
Beyond LoRA vs. Full Fine-Tuning: Gradient-Guided Optimizer Routing for LLM Adaptation
Gradient routing between full and LoRA tuning beats static choices
arxiv:2605.07111 v2 · 2026-05-08 · cs.CL · cs.AI
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{7X2WC3QOGBPMK2NTU7Z6JHGROH}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
Our evaluations show that MoLF either improves on or stays within 1.5% of the better of FFT and LoRA across all settings, while MoLF-Efficient outperforms prior adaptive LoRA approaches by up to 20% on Fact and 9% on Med and SQL.
That gradient-guided routing at the optimizer level will produce stable training dynamics and that the observed performance gains on the tested models and tasks will hold for other LLMs and domains.
MoLF routes updates between full fine-tuning and LoRA at the optimizer level to match or exceed the better of either static method, with an efficient LoRA-only variant outperforming prior adaptive approaches.
Formal links
Receipt and verification
| First computed | 2026-05-20T00:04:34.544123Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
fdf5616e0e305ec569b3a7f3e49cd171d4fecd9ccf93f69aa1767c03d5dea13a
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/7X2WC3QOGBPMK2NTU7Z6JHGROH \
| 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: fdf5616e0e305ec569b3a7f3e49cd171d4fecd9ccf93f69aa1767c03d5dea13a
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "8e5bf3075d2e1b68b45eb49719ba7ea8b7e781e48d2aac672b64f638cb815090",
"cross_cats_sorted": [
"cs.AI"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.CL",
"submitted_at": "2026-05-08T01:38:58Z",
"title_canon_sha256": "103e0cf8c60a2787cbd5b3f86bad6499148fd2bfa103ee1f751146f704ee3b64"
},
"schema_version": "1.0",
"source": {
"id": "2605.07111",
"kind": "arxiv",
"version": 2
}
}