pith:DWT2XANH
MTA: Multi-Granular Trajectory Alignment for Large Language Model Distillation
Multi-granular trajectory alignment improves knowledge distillation by matching teacher and student representations at word level in lower layers and phrase level in higher layers.
arxiv:2605.01374 v2 · 2026-05-02 · cs.CL
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{DWT2XANHCKBJC72665A4EUJWDL}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
MTA consistently outperforms state-of-the-art baselines on standard benchmarks, with ablations confirming the contribution of each component.
That aligning teacher and student representations along their layer-wise transformation trajectory using a layer-adaptive multi-granular strategy (word-level lower, phrase-level higher) will better guide the student to capture the teacher's internal relational structure than fixed-layer or token-level methods.
MTA improves LLM knowledge distillation by aligning representations along layer-wise trajectories with adaptive granularity from words to phrases using dynamic structural and hidden representation alignment losses.
Receipt and verification
| First computed | 2026-06-03T01:05:50.830716Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
1da7ab81a71282917f5ef741c251361af80bd16acabf1112ad0d1860bd263913
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/DWT2XANHCKBJC72665A4EUJWDL \
| 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: 1da7ab81a71282917f5ef741c251361af80bd16acabf1112ad0d1860bd263913
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "4a209011ec524ab89114606c2795774c10a891a1e4d1f64f66f42de78d4ce61e",
"cross_cats_sorted": [],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.CL",
"submitted_at": "2026-05-02T10:52:49Z",
"title_canon_sha256": "1b270c6c37c74de47904b5efb3f575514dfda75bb956d0009de8d7354a426b05"
},
"schema_version": "1.0",
"source": {
"id": "2605.01374",
"kind": "arxiv",
"version": 2
}
}