# Hallucination Evaluation on POPE COCO 2014 (Adversarial) Source: [Hallucination Evaluation on POPE COCO 2014 (Adversarial)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:31:53.597Z Evaluation of model hallucination capabilities using the Adversarial configuration of the POPE benchmark applied to the COCO 2014 dataset, reporting Accuracy and F1 scores. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Hallucination Evaluation | | Dataset (including any stated split) | POPE COCO 2014 (Adversarial) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 13 of 13 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Accuracy](): Higher is better; unit: PERCENT. - [F1 Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | VEGAS | 81.43 | Not recorded | 6940e79e456146936284f82b | | VISTA | 81.3 | Not recorded | 6940e79e456146936284f82b | | PAI | 81.05 | Not recorded | 6940e79e456146936284f82b | | Vanilla | 80.03 | Not recorded | 6940e79e456146936284f82b | | VCD | 79.95 | Not recorded | 6940e79e456146936284f82b | | VEGAS | 78.94 | Not recorded | 6940e79e456146936284f82b | | Vanilla | 78.68 | Not recorded | 6940e79e456146936284f82b | | PAI | 78.68 | Not recorded | 6940e79e456146936284f82b | | VISTA | 78.63 | Not recorded | 6940e79e456146936284f82b | | VEGAS | 72.77 | Not recorded | 6940e79e456146936284f82b | | VISTA | 72.47 | Not recorded | 6940e79e456146936284f82b | | PAI | 71.7 | Not recorded | 6940e79e456146936284f82b | | Vanilla | 71.13 | Not recorded | 6940e79e456146936284f82b | ### VEGAS Accuracy: 81.43. Result ID: 699852025698665ec4afbac9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"LLaVA-1.5","Decoding Strategy":"Greedy"}. This record does not assert independent reproduction. ### VISTA Accuracy: 81.3. Result ID: 699852025698665ec4afbac8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"LLaVA-1.5","Decoding Strategy":"Greedy"}. This record does not assert independent reproduction. ### PAI Accuracy: 81.05. Result ID: 699852025698665ec4afbac7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"LLaVA-1.5","Decoding Strategy":"Greedy"}. This record does not assert independent reproduction. ### Vanilla Accuracy: 80.03. Result ID: 699852025698665ec4afbac5. [Reporting paper]() Recorded evaluation configuration: {"Base Model":"LLaVA-1.5","Decoding Strategy":"Greedy"}. This record does not assert independent reproduction. ### VCD Accuracy: 79.95. Result ID: 699852025698665ec4afbac6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"LLaVA-1.5","Decoding Strategy":"Greedy"}. This record does not assert independent reproduction. ### VEGAS Accuracy: 78.94. Result ID: 699852025698665ec4afbad1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Shikra","Decoding Strategy":"Greedy"}. This record does not assert independent reproduction. ### Vanilla Accuracy: 78.68. Result ID: 699852025698665ec4afbace. [Reporting paper]() Recorded evaluation configuration: {"Base Model":"Shikra","Decoding Strategy":"Greedy"}. This record does not assert independent reproduction. ### PAI Accuracy: 78.68. Result ID: 699852025698665ec4afbacf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Shikra","Decoding Strategy":"Greedy"}. This record does not assert independent reproduction. ### VISTA Accuracy: 78.63. Result ID: 699852025698665ec4afbad0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Shikra","Decoding Strategy":"Greedy"}. This record does not assert independent reproduction. ### VEGAS Accuracy: 72.77. Result ID: 699852025698665ec4afbacd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"MiniGPT-4","Decoding Strategy":"Greedy"}. This record does not assert independent reproduction. ### VISTA Accuracy: 72.47. Result ID: 699852025698665ec4afbacc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"MiniGPT-4","Decoding Strategy":"Greedy"}. This record does not assert independent reproduction. ### PAI Accuracy: 71.7. Result ID: 699852025698665ec4afbacb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"MiniGPT-4","Decoding Strategy":"Greedy"}. This record does not assert independent reproduction. ### Vanilla Accuracy: 71.13. Result ID: 699852025698665ec4afbaca. [Reporting paper]() Recorded evaluation configuration: {"Base Model":"MiniGPT-4","Decoding Strategy":"Greedy"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.