pith:QWHABWM5
Self-Consistency from Only Two Samples: CoT-PoT Ensembling for Efficient LLM Reasoning
CoT-PoT ensembling cuts the samples needed for LLM self-consistency by 9.3 times while raising accuracy.
arxiv:2604.17433 v2 · 2026-04-19 · cs.CL · cs.AI · cs.LG
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{QWHABWM5WU2ONX3LANLUMMT6G5}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
CoT-PoT ensembling not only improves overall accuracy, but also drastically reduces the number of samples required for SC by a factor of 9.3x. In particular, the majority of tasks (78.6%) can be addressed with only two samples, which has not been possible with any prior SC methods.
The assumption that Chain-of-Thought and Program-of-Thought outputs are sufficiently complementary and that their agreement reliably indicates correctness without needing many more samples or introducing new error modes; this is implicit in the early-stopping and ensembling strategies described.
CoT-PoT ensembling achieves self-consistency accuracy in LLMs with only two samples for 78.6% of tasks, reducing computation by 9.3x compared to standard methods.
Receipt and verification
| First computed | 2026-06-08T01:04:05.108686Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
858e00d99db534e6df6b035746327e3753e2c8efbcd59aafd69fe45a91df95c5
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/QWHABWM5WU2ONX3LANLUMMT6G5 \
| 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: 858e00d99db534e6df6b035746327e3753e2c8efbcd59aafd69fe45a91df95c5
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "dbce1aacf91604acd645fe32afc726af664aa40b9c279d95d4a9dc5975db7dd3",
"cross_cats_sorted": [
"cs.AI",
"cs.LG"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.CL",
"submitted_at": "2026-04-19T13:26:04Z",
"title_canon_sha256": "a9fd41b9e06820428d3d1acad47bac315c3f27c9739baef71a919b65c4b77778"
},
"schema_version": "1.0",
"source": {
"id": "2604.17433",
"kind": "arxiv",
"version": 2
}
}