Pith Number

pith:IATM46SH

pith:2022:IATM46SH4DVYTKK5TNAGKNUSLU

not attested not anchored not stored refs resolved

LaMDA: Language Models for Dialog Applications

Aaron Cohen, Adam Roberts, Alejandra Molina, Alena Butryna, Alicia Jin, Amin Ghafouri, Apoorv Kulshreshtha, Ben Hutchinson, Ben Zevenbergen, Blaise Aguera-Arcas, Chung-Ching Chang, Claire Cui, Daniel De Freitas, Dehao Chen, Dmitry Lepikhin, Ed Chi, Erin Hoffman-John, Heng-Tze Cheng, Hongrae Lee, Huaixiu Steven Zheng, Igor Krivokon, James Qin, Jamie Hall, Joe Fenton, Johnny Soraker, Josh Lee, Kathleen Meier-Hellstern, Kristen Olson, Laichee Man, Leslie Baker, Lora Aroyo, Maarten Bosma, Marcelo Menegali, Marc Pickett, Marian Croak, Mark Diaz, Matthew Lamm, Maxim Krikun, Meredith Ringel Morris, Noam Shazeer, Pranesh Srinivasan, Quoc Le, Rachel Bernstein, Ravi Rajakumar, Ray Kurzweil, Renelito Delos Santos, Romal Thoppilan, Taylor Bos, Toju Duke, Tulsee Doshi, Viktoriya Kuzmina, Vincent Zhao, Vinodkumar Prabhakaran, Will Rusch, Yaguang Li, Yanping Huang, Yanqi Zhou, Yuanzhong Xu, Yu Du, Zhifeng Chen

Fine-tuning LaMDA models on annotated human values plus access to external tools markedly raises safety and factual grounding in dialog responses.

arxiv:2201.08239 v3 · 2022-01-20 · 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{IATM46SH4DVYTKK5TNAGKNUSLU}

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

fine-tuning with annotated data and enabling the model to consult external knowledge sources can lead to significant improvements towards the two key challenges of safety and factual grounding.

C2weakest assumption

The assumption that the illustrative set of human values used for annotation and the chosen external knowledge sources (IR, translator, calculator) are sufficient to capture the full range of safety and factuality requirements in open-ended real-world dialogs.

C3one line summary

LaMDA shows that fine-tuning on human-value annotations and consulting external knowledge sources significantly improves safety and factual grounding in large dialog models beyond what scaling alone achieves.

References

120 extracted · 120 resolved · 15 Pith anchors

[1] Skip-thought vectors 2015

[2] Semi-supervised sequence learning 2015

[3] Deep contextualized word representations 2018

[5] Improving language understanding by generative pre-training 2018

[6] BERT: Pre-training of deep bidirectional transformers for language understanding 2019

Cited by

88 papers in Pith

In-Context Model Predictive Generation: Open-Vocabulary Motion Synthesis from Language Models to Physics

SharQ: Bridging Activation Sparsity and FP4 Quantization for LLM Inference

Real-Time Language Model Jamming: A Case Study for Live Music Accompaniment Generation

Decoding Multimodal Cues: Unveiling the Implicit Meaning Behind Hateful Videos

Provably Efficient Personalized Multi-Objective Bandits with Proactive Conversational Queries

Receipt and verification

First computed	2026-07-05T03:55:51.905047Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

4026ce7a47e0eb89a95d9b406536925d22b467f63c263f343b9c783534b813f3

Aliases

arxiv: 2201.08239 · arxiv_version: 2201.08239v3 · doi: 10.48550/arxiv.2201.08239 · pith_short_12: IATM46SH4DVY · pith_short_16: IATM46SH4DVYTKK5 · pith_short_8: IATM46SH

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/IATM46SH4DVYTKK5TNAGKNUSLU \
  | 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: 4026ce7a47e0eb89a95d9b406536925d22b467f63c263f343b9c783534b813f3

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "892b8542925d98985ea67a8ae2d0bd8a9db63b98cc9737b2a1e4216b953ea86b",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2022-01-20T15:44:37Z",
    "title_canon_sha256": "7eb86eef1745306f09fec4112d4b5fe83e79a6ddecbb9cbe3dee886ae97357dd"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2201.08239",
    "kind": "arxiv",
    "version": 3
  }
}