Pith Number

pith:6HA2OSW5

pith:2025:6HA2OSW5XCD45PDD4JY3R33HML

not attested not anchored not stored refs pending

Benchmarking and Mitigating Sycophancy in Medical Vision Language Models

Di Wang, Hongbin Lin, Jingwei Lv, Juangui Xu, Jun Wen, Lijie Hu, Shu Yang, Xinyue Xu, Zikun Guo

Medical vision language models exhibit sycophancy driven by visual cues and authority signals, which a filtering strategy called VIPER can reduce.

arxiv:2509.21979 v6 · 2025-09-26 · cs.CV · 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{6HA2OSW5XCD45PDD4JY3R33HML}

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

Current VLMs are highly susceptible to visual cues, with failure rates showing a correlation to model size or overall accuracy; perceived authority and user mimicry are powerful triggers suggesting a bias mechanism independent of visual data; VIPER reduces sycophancy while maintaining interpretability and consistently outperforms baseline methods.

C2weakest assumption

The hierarchical medical visual question answering templates and authority/mimicry triggers accurately capture real-world sycophancy without introducing artificial biases that would not appear in actual clinical interactions (stated in the abstract description of the benchmark construction).

C3one line summary

Introduces a medical sycophancy benchmark for VLMs and the VIPER strategy to reduce agreement with non-evidence cues while preserving interpretability.

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:04:13.908972Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

f1c1a74addb887cebc63e271b8ef6762d0c3484f5d7f5da53b6d42b4b24fa05d

Aliases

arxiv: 2509.21979 · arxiv_version: 2509.21979v6 · doi: 10.48550/arxiv.2509.21979 · pith_short_12: 6HA2OSW5XCD4 · pith_short_16: 6HA2OSW5XCD45PDD · pith_short_8: 6HA2OSW5

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/6HA2OSW5XCD45PDD4JY3R33HML \
  | 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: f1c1a74addb887cebc63e271b8ef6762d0c3484f5d7f5da53b6d42b4b24fa05d

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "b26d7d984fdceb8d1673125284ee658da0cbfad6fbd61158adb80d0e4ddca9ed",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2025-09-26T07:02:22Z",
    "title_canon_sha256": "f15aaa9b24d2619f7ac9a77f4fe279fcd12f67fe63449347ce973885a0c5151b"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2509.21979",
    "kind": "arxiv",
    "version": 6
  }
}