pith:UHXFDEJW
Parameter-Efficient Neuroevolution for Diverse LLM Generation: Quality-Diversity Optimization via Prompt Embedding Evolution
Evolving compact prompt embeddings inside frozen large language models produces more diverse outputs than standard methods.
arxiv:2605.09781 v2 · 2026-05-10 · cs.NE · cs.AI · cs.CL · cs.LG
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{UHXFDEJWIC2UDGHU4WG4TOBCL2}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
On HumanEval (164 problems), MBPP, and creative writing benchmarks, QD-LLM achieves 46.4% higher coverage and 41.4% higher QD-Score than QDAIF (p<0.001, 30 runs, Vargha-Delaney A=0.94).
That hybrid semantic-plus-explicit behavior descriptors remain sufficiently independent (NMI = 0.08 ± 0.02) to support the formal coverage bounds of Theorem 1 and that prompt embeddings of ~32K parameters can reliably steer 70B+ frozen LLMs across the tested domains.
QD-LLM evolves prompt embeddings via neuroevolution in a quality-diversity framework, delivering 46% higher coverage and 41% higher QD-score than prior methods on coding and writing benchmarks.
Receipt and verification
| First computed | 2026-06-23T01:12:08.168300Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
a1ee51913640b54198f4e58dc9b8225ebc9cc008f8a78a4579883a3cfeae8003
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/UHXFDEJWIC2UDGHU4WG4TOBCL2 \
| 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: a1ee51913640b54198f4e58dc9b8225ebc9cc008f8a78a4579883a3cfeae8003
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "217074b293386fa91854a82f0b7692a482d477bf22e4e3dde7079bd30490fa69",
"cross_cats_sorted": [
"cs.AI",
"cs.CL",
"cs.LG"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"primary_cat": "cs.NE",
"submitted_at": "2026-05-10T22:00:15Z",
"title_canon_sha256": "e9dc7ee6fa6dcd19345458b189f00241e0bab47d5c04212ea8c44fb2f527aa93"
},
"schema_version": "1.0",
"source": {
"id": "2605.09781",
"kind": "arxiv",
"version": 2
}
}