Pith Number

pith:UFRUP7UU

pith:2021:UFRUP7UU7PYG7TMWUBMOA5ABHW

not attested not anchored not stored refs resolved

Prefix-Tuning: Optimizing Continuous Prompts for Generation

Percy Liang, Xiang Lisa Li

Prefix-tuning matches full fine-tuning on natural language generation by optimizing a small continuous prefix while freezing all language model parameters.

arxiv:2101.00190 v1 · 2021-01-01 · cs.CL

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{UFRUP7UU7PYG7TMWUBMOA5ABHW}

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

by learning only 0.1% of the parameters, prefix-tuning obtains comparable performance in the full data setting, outperforms fine-tuning in low-data settings, and extrapolates better to examples with topics unseen during training.

C2weakest assumption

That the attention mechanism in the frozen pretrained model can be sufficiently guided by the learned continuous prefix to control generation quality and generalization without any updates to the core parameters.

C3one line summary

Prefix-tuning matches or exceeds fine-tuning on NLG tasks by optimizing a continuous prefix using 0.1% of parameters while keeping the LM frozen.

References

85 extracted · 85 resolved · 3 Pith anchors

[1] Intrinsic dimen- sionality explains the effectiveness of language model fine-tuning 2020

[2] Anja Belz and Ehud Reiter. 2006. https://www.aclweb.org/anthology/E06-1040 Comparing automatic and human evaluation of NLG systems . In 11th Conference of the E uropean Chapter of the Association for 2006

[3] Language Models are Few-Shot Learners 2020 · arXiv:2005.14165

[4] Sumanth Dathathri, Andrea Madotto, Janice Lan, Jane Hung, Eric Frank, Piero Molino, Jason Yosinski, and Rosanne Liu. 2020. https://openreview.net/forum?id=H1edEyBKDS Plug and play language models: A s 2020

[7] Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, Bruna Morrone, Quentin De Laroussilhe, Andrea Gesmundo, Mona Attariyan, and Sylvain Gelly. 2019. http://proceedings.mlr.press/v97/houlsby19a.html P 2019

Formal links

2 machine-checked theorem links

Cited by

87 papers in Pith

Structure Before Collapse: Transient semantic geometry in next-token prediction

The Hitchhiker's Guide to Agentic AI: From Foundations to Systems

The Professor: Multi-Teacher Unsupervised Prompt Distillation for Vision-Language Models

MindAlign: Decoding Inner Speech from fMRI Signals via Multimodal Embedding Alignment under Limited Data

EPnG: Adaptive Expert Prune-and-Grow for Parameter-Efficient MoE Fine-tuning

Receipt and verification

First computed	2026-07-05T02:04:16.156599Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

a16347fe94fbf06fcd96a058e074013d8d922c69db902c1d75f5873c21809958

Aliases

arxiv: 2101.00190 · arxiv_version: 2101.00190v1 · doi: 10.48550/arxiv.2101.00190 · pith_short_12: UFRUP7UU7PYG · pith_short_16: UFRUP7UU7PYG7TMW · pith_short_8: UFRUP7UU

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/UFRUP7UU7PYG7TMWUBMOA5ABHW \
  | 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: a16347fe94fbf06fcd96a058e074013d8d922c69db902c1d75f5873c21809958

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "5f488c99bef40ee4bf91d95e6365705f4da5df1d524f20415f44929cb3f0f82b",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2021-01-01T08:00:36Z",
    "title_canon_sha256": "5e95707dfa06340e2187bf16864938cc11ab27cc60957fa2fe318fed885b1310"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2101.00190",
    "kind": "arxiv",
    "version": 1
  }
}