pith. sign in
Pith Number

pith:6IXVWWO4

pith:2024:6IXVWWO4WRT5VT36XR6GW7BB26
not attested not anchored not stored refs resolved

Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking

Eric Zelikman, Georges Harik, Nick Haber, Noah D. Goodman, Varuna Jayasiri, Yijia Shao

Language models learn to generate rationales before each token during pretraining to improve future predictions.

arxiv:2403.09629 v2 · 2024-03-14 · cs.CL · cs.AI · cs.LG

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{6IXVWWO4WRT5VT36XR6GW7BB26}

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

after continued pretraining of an LM on a corpus of internet text with Quiet-STaR, we find zero-shot improvements on GSM8K (5.9%→10.9%) and CommonsenseQA (36.3%→47.2%) and observe a perplexity improvement of difficult tokens in natural text. Crucially, these improvements require no fine-tuning on these tasks.

C2weakest assumption

that language models can initially learn to generate and effectively use internal rationales at each token to improve future text predictions, despite starting without knowledge of how to produce or apply such thoughts.

C3one line summary

Quiet-STaR lets language models learn token-level rationales from general text, producing zero-shot gains on GSM8K and CommonsenseQA after continued pretraining.

References

8 extracted · 8 resolved · 0 Pith anchors

[1] Ruocheng Wang, Eric Zelikman, Gabriel Poesia, Yewen Pu, Nick Haber, and Noah D Goodman 2022
[2] Janet sells an average of 12 fresh duck eggs daily on the farmers ' market. If she sells them for $2 per egg how much does she make per week, assuming she sells at the farmers ' market most every day?
[3] The ducks lay 16 eggs per day
[4] She eats 3 for breakfast every morning
[5] She bakes muffins for her friends every day with 4

Cited by

32 papers in Pith

Receipt and verification
First computed 2026-05-17T23:38:48.938887Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

f22f5b59dcb467dacf7ebc7c6b7c21d7923b2c8f7ab649fb3b91f13d073fad22

Aliases

arxiv: 2403.09629 · arxiv_version: 2403.09629v2 · doi: 10.48550/arxiv.2403.09629 · pith_short_12: 6IXVWWO4WRT5 · pith_short_16: 6IXVWWO4WRT5VT36 · pith_short_8: 6IXVWWO4
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/6IXVWWO4WRT5VT36XR6GW7BB26 \
  | 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: f22f5b59dcb467dacf7ebc7c6b7c21d7923b2c8f7ab649fb3b91f13d073fad22
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "f4409e4df469e5e7ae3e3127a2895fc4e2c1d886a715f729ec104cf299962786",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.LG"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2024-03-14T17:58:16Z",
    "title_canon_sha256": "58f96fea8ecf1be0ee9111de3692519516364c20b44332de0796546b9a2d27b3"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2403.09629",
    "kind": "arxiv",
    "version": 2
  }
}