# Object Hallucination Detection on POPE random Source: [Object Hallucination Detection on POPE random]() Collection index: [llms.txt]() Data updated: 2026-05-28T09:01:57.322Z Evaluation of model performance on detecting object hallucinations using the POPE dataset, specifically focusing on the 'random' configuration or split, reporting F1 score and Trigger Percentage (Trig.%). 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 | Object Hallucination Detection | | Dataset (including any stated split) | POPE random | | Metric | F1 Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 6 of 6 | | 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 - [F1 Score](): Higher is better; unit: PERCENT. - [Trigger Percentage](): Higher is better; unit: PERCENT. ## Recorded results | Method | F1 Score | Result date | Report paper | | --- | --- | --- | --- | | RSP | 89.1 | Not recorded | 6a17cc01dbd7150506f81241 | | Baseline | 88.7 | Not recorded | 6a17cc01dbd7150506f81241 | | Always-on | 87.4 | Not recorded | 6a17cc01dbd7150506f81241 | | RSP | 0.899 | Not recorded | 6a17cc01dbd7150506f81241 | | Baseline | 0.896 | Not recorded | 6a17cc01dbd7150506f81241 | | Always-on | 0.889 | Not recorded | 6a17cc01dbd7150506f81241 | ### RSP F1 Score: 89.1. Result ID: 6a18038afbc373592c11e3be. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"InstructBLIP","Prompting Strategy":"Selective Prompting (RSP)","Routing Mechanism":"inverse top-1 confidence","Prompt Text":"Be careful."}. This record does not assert independent reproduction. ### Baseline F1 Score: 88.7. Result ID: 6a18038afbc373592c11e3bc. [Reporting paper]() Recorded evaluation configuration: {"Model":"InstructBLIP"}. This record does not assert independent reproduction. ### Always-on F1 Score: 87.4. Result ID: 6a18038afbc373592c11e3bd. [Reporting paper]() Recorded evaluation configuration: {"Model":"InstructBLIP","Prompting Strategy":"Always-on","Prompt Text":"Be careful."}. This record does not assert independent reproduction. ### RSP F1 Score: 0.899. Result ID: 6a18038afbc373592c11e3c7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LLaVA-1.5","Routing Layer":"L23"}. This record does not assert independent reproduction. ### Baseline F1 Score: 0.896. Result ID: 6a18038afbc373592c11e3c5. [Reporting paper]() Recorded evaluation configuration: {"Model":"LLaVA-1.5"}. This record does not assert independent reproduction. ### Always-on F1 Score: 0.889. Result ID: 6a18038afbc373592c11e3c6. [Reporting paper]() Recorded evaluation configuration: {"Model":"LLaVA-1.5"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.