pith:GQ3K7COZ
GEASS: Gated Evidence-Adaptive Selective Caption Trust for Vision-Language Models
GEASS lets vision-language models decide per query how much of a self-generated caption to trust, cutting hallucinations.
arxiv:2605.01733 v2 · 2026-05-03 · cs.CV · cs.AI
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{GQ3K7COZB6FCUBKXM57QUKKDGQ}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
Experiments on POPE and HallusionBench across four VLMs show that GEASS consistently improves over vanilla inference and contrastive decoding, with only two extra forward passes per query.
That the combination of clean-path confidence and entropy reduction reliably identifies when and how much caption content is useful without discarding beneficial information or introducing new selection bias on a per-query basis.
GEASS selectively gates and weights self-generated captions using confidence and entropy to reduce object hallucinations in VLMs, outperforming vanilla inference and contrastive decoding on POPE and HallusionBench.
Receipt and verification
| First computed | 2026-05-20T01:05:15.137695Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
3436af89d90f8a2a0557677f0a2943343fd1ef2d654eac0a4622ecb755f33a4a
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/GQ3K7COZB6FCUBKXM57QUKKDGQ \
| 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: 3436af89d90f8a2a0557677f0a2943343fd1ef2d654eac0a4622ecb755f33a4a
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "a4000909f9852b0a7fd1b5d98d26b4e96c721160b63e30494fc79a09fe385781",
"cross_cats_sorted": [
"cs.AI"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"primary_cat": "cs.CV",
"submitted_at": "2026-05-03T06:09:04Z",
"title_canon_sha256": "3ff95be860c28c40322b7bf26b65e24c59f0bd7facc4dec79c1051cd5999e4c9"
},
"schema_version": "1.0",
"source": {
"id": "2605.01733",
"kind": "arxiv",
"version": 2
}
}