Pith Number

pith:IST3XHVN

pith:2023:IST3XHVNJSADRSBL5L6JRTVLNT

not attested not anchored not stored refs resolved

Instruction Tuning with GPT-4

Baolin Peng, Chunyuan Li, Jianfeng Gao, Michel Galley, Pengcheng He

GPT-4 generated instruction data enables LLaMA models to reach higher zero-shot performance on new tasks than earlier synthetic datasets.

arxiv:2304.03277 v1 · 2023-04-06 · cs.CL · cs.AI

Open paper page JSON What is a Pith Number?

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

Claims

C1strongest claim

Our early experiments on instruction-tuned LLaMA models show that the 52K English and Chinese instruction-following data generated by GPT-4 leads to superior zero-shot performance on new tasks to the instruction-following data generated by previous state-of-the-art models.

C2weakest assumption

That performance gains on the chosen zero-shot tasks reflect genuine improvement in instruction following rather than artifacts of GPT-4's data generation process or evaluation choices.

C3one line summary

GPT-4-generated instruction data produces superior zero-shot performance in finetuned LLaMA models versus prior state-of-the-art data.

References

18 extracted · 18 resolved · 11 Pith anchors

[1] A General Language Assistant as a Laboratory for Alignment · arXiv:2112.00861

[2] Yejin Bang, Samuel Cahyawijaya, Nayeon Lee, Wenliang Dai, Dan Su, Bryan Wilie, Holy Lovenia, Ziwei Ji, Tiezheng Yu, Willy Chung, et al · doi:10.5281/zenodo.7733589

[3] Constitutional AI: Harmlessness from AI Feedback · arXiv:2212.08073

[4] GPT-Neo: Large Scale Autoregressive Language Modeling with Mesh-Tensorflow , March 2021 1901 · doi:10.5281/zenodo.5297715

[5] Scaling Instruction-Finetuned Language Models · arXiv:2210.11416

Formal links

1 machine-checked theorem link

Cited by

42 papers in Pith

SALMONN: Towards Generic Hearing Abilities for Large Language Models

MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning

Secrets of RLHF in Large Language Models Part I: PPO

Large Language Models are not Fair Evaluators

OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models

Receipt and verification

First computed	2026-05-17T23:39:22.359932Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

44a7bb9ead4c8038c82beafc98ceab6ce87f1de79c8e0b9e50615d9cc1fee7af

Aliases

arxiv: 2304.03277 · arxiv_version: 2304.03277v1 · doi: 10.48550/arxiv.2304.03277

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/IST3XHVNJSADRSBL5L6JRTVLNT \
  | 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: 44a7bb9ead4c8038c82beafc98ceab6ce87f1de79c8e0b9e50615d9cc1fee7af

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "a5fa7e08c14cfe870725a2b0ab026cc82993bc6daed0af6062dcbe35be363a91",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2023-04-06T17:58:09Z",
    "title_canon_sha256": "2da0c9d0dd1bb0ca8ff88374f47294a26d976e55871dbc5d18aa2d9f2cae193e"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2304.03277",
    "kind": "arxiv",
    "version": 1
  }
}