pith. sign in
Pith Number

pith:PT4Y6HGA

pith:2023:PT4Y6HGAZMHNPNEWKHV7KD2SCP
not attested not anchored not stored refs pending

Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback

Baolin Peng, Hao Cheng, Jianfeng Gao, Lars Liden, Michel Galley, Pengcheng He, Qiuyuan Huang, Weizhu Chen, Yu Hu, Yujia Xie, Zhou Yu

LLM-Augmenter augments black-box models like ChatGPT with external knowledge modules and automated feedback to reduce hallucinations while preserving fluency.

arxiv:2302.12813 v3 · 2023-02-24 · 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{PT4Y6HGAZMHNPNEWKHV7KD2SCP}

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

LLM-Augmenter significantly reduces ChatGPT's hallucinations without sacrificing the fluency and informativeness of its responses.

C2weakest assumption

That utility functions such as factuality scores can reliably detect and guide correction of hallucinations without introducing new errors or degrading response quality.

C3one line summary

LLM-Augmenter reduces hallucinations in LLMs like ChatGPT by grounding responses in external knowledge and using automated feedback loops to iteratively revise outputs.

Formal links

2 machine-checked theorem links

Cited by

26 papers in Pith

Gemini: A Family of Highly Capable Multimodal Models
Social and Ethical Risks Posed by General-Purpose LLMs for Settling Newcomers in Canada
Trustworthiness in Retrieval-Augmented Generation Systems: A Survey
From Cool Demos to Production-Ready FMware: Core Challenges and a Technology Roadmap
Library Hallucinations in LLM-Generated Code: A Risk Analysis Grounded in Developer Queries
Receipt and verification
First computed 2026-05-17T23:38:14.429196Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

7cf98f1cc0cb0ed7b49651ebf50f5213c30335fbc700e348a272bdc58cae7d5e

Aliases

arxiv: 2302.12813 · arxiv_version: 2302.12813v3 · doi: 10.48550/arxiv.2302.12813 · pith_short_12: PT4Y6HGAZMHN · pith_short_16: PT4Y6HGAZMHNPNEW · pith_short_8: PT4Y6HGA
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/PT4Y6HGAZMHNPNEWKHV7KD2SCP \
  | 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: 7cf98f1cc0cb0ed7b49651ebf50f5213c30335fbc700e348a272bdc58cae7d5e
Canonical record JSON 
{
  "metadata": {
    "abstract_canon_sha256": "15e69d9cba5b57e7fccaf618e490af2ec4523001c530954e7fb5af1e364bf0c2",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2023-02-24T18:48:43Z",
    "title_canon_sha256": "e76cb4409e5a4f1b7c262877010a2f67881ae0ff3f7f7c5dbae51b8faca4f459"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2302.12813",
    "kind": "arxiv",
    "version": 3
  }
}