Pith Number

pith:5LRDWUDF

pith:2023:5LRDWUDFJ26DRAZG2B6G5FXNC7

not attested not anchored not stored refs resolved

Enhancing Chat Language Models by Scaling High-quality Instructional Conversations

Bokai Xu, Bowen Zhou, Maosong Sun, Ning Ding, Shengding Hu, Yujia Qin, Yulin Chen, Zhiyuan Liu, Zhi Zheng

Scaling AI-generated multi-turn conversations to 1.5 million dialogues produces a fine-tuned LLaMA that outperforms Vicuna.

arxiv:2305.14233 v1 · 2023-05-23 · 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{5LRDWUDFJ26DRAZG2B6G5FXNC7}

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

Building upon UltraChat, we fine-tune a LLaMA model to create a powerful conversational model, UltraLLaMA. Our evaluations indicate that UltraLLaMA consistently outperforms other open-source models, including Vicuna, the previously recognized state-of-the-art open-source model.

C2weakest assumption

That conversations generated entirely by AI without any human queries can still capture the breadth, coherence, and instructional quality needed to produce measurable gains over prior open-source chat models.

C3one line summary

UltraChat supplies 1.5 million high-quality multi-turn dialogues that, when used to fine-tune LLaMA, produce UltraLLaMA, which outperforms prior open-source chat models including Vicuna.

References

253 extracted · 253 resolved · 15 Pith anchors

[1] Chatgpt: Optimizing language models for dialogue , author=. OpenAI , year=

[3] GPT-4 technical report , author=. arXiv , year=

[4] Stanford Center for Research on Foundation Models 2023

[6] Advances in neural information processing systems , volume=

[7] Compacter: Efficient low-rank hypercomplex adapter layers , url =

Formal links

2 machine-checked theorem links

Cited by

35 papers in Pith

Convex Optimization for Alignment and Preference Learning on a Single GPU

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs

What Is Preference Optimization Doing, and Why?

DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices

Receipt and verification

First computed	2026-05-17T23:38:50.734984Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

eae23b50654ebc388326d07c6e96ed17e20055d87fbcbff8ab4e06501dafc418

Aliases

arxiv: 2305.14233 · arxiv_version: 2305.14233v1 · doi: 10.48550/arxiv.2305.14233 · pith_short_12: 5LRDWUDFJ26D · pith_short_16: 5LRDWUDFJ26DRAZG · pith_short_8: 5LRDWUDF

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/5LRDWUDFJ26DRAZG2B6G5FXNC7 \
  | 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: eae23b50654ebc388326d07c6e96ed17e20055d87fbcbff8ab4e06501dafc418

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "2b60115e306281141dee36bead52e70a84f177e6a39969bb78c069fb103e628b",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2023-05-23T16:49:14Z",
    "title_canon_sha256": "9a780193da84cb1bd703e08534f7722eac8065f6a9ac320fa71c8cf18bfefcbb"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2305.14233",
    "kind": "arxiv",
    "version": 1
  }
}