Pith Number

pith:BEEPPANH

pith:2026:BEEPPANHT7JYG5CUQZEJHOS5GN

not attested not anchored not stored refs resolved

PEML: Parameter-efficient Multi-Task Learning with Optimized Continuous Prompts

Anjir Ahmed Chowdhury, Feng Yan, Syed Zawad, Xiaolong Ma, Xu Dong

PEML jointly optimizes continuous prompts via neural architecture engineering and low-rank model adaptation to improve multi-task LLM performance.

arxiv:2605.14055 v1 · 2026-05-13 · cs.CL · cs.AI

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{BEEPPANHT7JYG5CUQZEJHOS5GN}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

The evaluation results present an average accuracy improvement of up to 6.67%, with individual tasks showing peak gains of up to 10.75%.

C2weakest assumption

The assumption that the proposed neural architecture for prompt optimization combined with low-rank adaptation will consistently outperform existing methods across diverse tasks without introducing new overfitting risks or requiring extensive hyperparameter tuning.

C3one line summary

PEML co-optimizes continuous prompts and low-rank adaptations to deliver up to 6.67% average accuracy gains over existing multi-task PEFT methods on GLUE, SuperGLUE, and other benchmarks.

References

97 extracted · 97 resolved · 31 Pith anchors

[1] International conference on machine learning , pages= 2022

[2] Parameter-efficient multi-task fine-tuning for transformers via shared hypernetworks , author=. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th Int

[3] Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=

[4] H yper L o RA : Efficient Cross-task Generalization via Constrained Low-Rank Adapters Generation 2024 · doi:10.18653/v1/2024.findings-emnlp.956

[5] Lorahub: Efficient cross-task generalization via dynamic lora composition

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-17T23:39:12.594773Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

0908f781a79fd3837454864893ba5d3357f36033a7b82dab097a859bc3602e46

Aliases

arxiv: 2605.14055 · arxiv_version: 2605.14055v1 · doi: 10.48550/arxiv.2605.14055 · pith_short_12: BEEPPANHT7JY · pith_short_16: BEEPPANHT7JYG5CU · pith_short_8: BEEPPANH

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/BEEPPANHT7JYG5CUQZEJHOS5GN \
  | 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: 0908f781a79fd3837454864893ba5d3357f36033a7b82dab097a859bc3602e46

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "53897c4ab277593fdb92e8c62791cdb60861459126d2af0aa18afe2794f92c69",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-05-13T19:25:56Z",
    "title_canon_sha256": "6b3ce4330a7604415b95ab0a7f2b67c83dc2b2059c667630bce188b19287ab06"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14055",
    "kind": "arxiv",
    "version": 1
  }
}