Pith Number

pith:555TZ7WG

pith:2023:555TZ7WGIQESUA54MQKZTEW5X4

not attested not anchored not stored refs resolved

Evaluating Object Hallucination in Large Vision-Language Models

Jinpeng Wang, Ji-Rong Wen, Kun Zhou, Wayne Xin Zhao, Yifan Du, Yifan Li

Large vision-language models often describe objects absent from the given image, especially those frequent in instructions or co-occurring with visible items.

arxiv:2305.10355 v3 · 2023-05-17 · cs.CV · cs.CL · cs.MM

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{555TZ7WGIQESUA54MQKZTEW5X4}

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

LVLMs mostly suffer from severe object hallucination issue... objects that frequently occur in the visual instructions or co-occur with the image objects, are obviously prone to be hallucinated by LVLMs... our POPE can evaluate the object hallucination in a more stable and flexible way.

C2weakest assumption

That the selected representative LVLMs and visual instruction datasets are sufficiently typical of the broader class of models, and that the polling queries in POPE do not introduce new systematic biases in measuring hallucination.

C3one line summary

Large vision-language models exhibit severe object hallucination that varies with training instructions, and the proposed POPE polling method evaluates it more stably and flexibly than prior approaches.

References

40 extracted · 40 resolved · 12 Pith anchors

[1] nocaps: novel object captioning at scale , url= 2019 · doi:10.1109/iccv.2019.00904

[2] Menick, Sebastian Borgeaud, Andy Brock, Aida Nematzadeh, Sahand Sharifzadeh, Mikolaj Binkowski, Ricardo Barreira, Oriol Vinyals, Andrew Zisserman, and Kar \' e n Simonyan 2022

[3] Lawrence Zitnick, and Devi Parikh 2015

[4] Lawrence Zitnick, and Devi Parikh 2015 · doi:10.1109/iccv.2015.279

[5] Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond 2023 · arXiv:2308.12966

Formal links

2 machine-checked theorem links

Cited by

118 papers in Pith

Dive Into the Implicit Biases of Low-rank Vision-language Alignment

The inattentional gap in task conditioned AI models that omit otherwise reportable safety critical signals

SharQ: Bridging Activation Sparsity and FP4 Quantization for LLM Inference

On the Sparsity-Storage-Accuracy Tradeoff in Parsimoniously Activated Dictionary Learning

HPP: Hierarchical Programmatic Probing for Long Video Understanding by Decoupling Perception and Reasoning

Receipt and verification

First computed	2026-07-05T07:05:08.636573Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

ef7b3cfec644092a03bc64159992ddbf37951e3046db8bc43f435e7caacee1ad

Aliases

arxiv: 2305.10355 · arxiv_version: 2305.10355v3 · doi: 10.48550/arxiv.2305.10355 · pith_short_12: 555TZ7WGIQES · pith_short_16: 555TZ7WGIQESUA54 · pith_short_8: 555TZ7WG

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/555TZ7WGIQESUA54MQKZTEW5X4 \
  | 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: ef7b3cfec644092a03bc64159992ddbf37951e3046db8bc43f435e7caacee1ad

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "931ab8ddd1af19b56486cde173c84c852ca8f723971792b5bbdde6d56726f174",
    "cross_cats_sorted": [
      "cs.CL",
      "cs.MM"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2023-05-17T16:34:01Z",
    "title_canon_sha256": "58ea4de77f6f74bc1927472cc5d620ed7d1e0d77b59e3fd907bb8cb07f8d5f53"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2305.10355",
    "kind": "arxiv",
    "version": 3
  }
}