# Object Hallucination Detection on POPE popular Source: [Object Hallucination Detection on POPE popular]() Collection index: [llms.txt]() Data updated: 2026-06-29T06:38:47.898Z Evaluation of model performance on detecting object hallucinations using the 'popular' subset of the POPE dataset, 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 popular | | Metric | F1 Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 27 of 27 | | 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 | | --- | --- | --- | --- | | OPERA | 86.59 | Not recorded | 6a41fc1b206542251d7ccb79 | | RSP | 86.5 | Not recorded | 6a17cc01dbd7150506f81241 | | Baseline | 86.4 | Not recorded | 6a17cc01dbd7150506f81241 | | Fox | 86.3 | Not recorded | 6a41fc1b206542251d7ccb79 | | Always-on | 86.2 | Not recorded | 6a17cc01dbd7150506f81241 | | CausalMM | 86.17 | Not recorded | 6a41fc1b206542251d7ccb79 | | SID | 85.21 | Not recorded | 6a41fc1b206542251d7ccb79 | | RSP | 85.2 | Not recorded | 6a17cc01dbd7150506f81241 | | Always-on | 84.2 | Not recorded | 6a17cc01dbd7150506f81241 | | ICD | 84.18 | Not recorded | 6a41fc1b206542251d7ccb79 | | Baseline | 83.9 | Not recorded | 6a17cc01dbd7150506f81241 | | Fox | 83.77 | Not recorded | 6a41fc1b206542251d7ccb79 | | SID | 83.51 | Not recorded | 6a41fc1b206542251d7ccb79 | | Sampling | 83.4 | Not recorded | 6a41fc1b206542251d7ccb79 | | CausalMM | 83.27 | Not recorded | 6a41fc1b206542251d7ccb79 | | OPERA | 83.21 | Not recorded | 6a41fc1b206542251d7ccb79 | | OPERA | 83.19 | Not recorded | 6a41fc1b206542251d7ccb79 | | CausalMM | 82.89 | Not recorded | 6a41fc1b206542251d7ccb79 | | Fox | 82.27 | Not recorded | 6a41fc1b206542251d7ccb79 | | VCD | 82.05 | Not recorded | 6a41fc1b206542251d7ccb79 | | ICD | 81.74 | Not recorded | 6a41fc1b206542251d7ccb79 | | Sampling | 81.55 | Not recorded | 6a41fc1b206542251d7ccb79 | | VCD | 81.12 | Not recorded | 6a41fc1b206542251d7ccb79 | | VCD | 81.12 | Not recorded | 6a41fc1b206542251d7ccb79 | | Sampling | 81.06 | Not recorded | 6a41fc1b206542251d7ccb79 | | ICD | 80.2 | Not recorded | 6a41fc1b206542251d7ccb79 | | SID | 79.97 | Not recorded | 6a41fc1b206542251d7ccb79 | ### OPERA F1 Score: 86.59. Result ID: 6a4212f0fbc373592c868736. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"LVLM backbone":"LLaVA-1.5"}. This record does not assert independent reproduction. ### RSP F1 Score: 86.5. Result ID: 6a18038afbc373592c11e3ca. [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: 86.4. Result ID: 6a18038afbc373592c11e3c8. [Reporting paper]() Recorded evaluation configuration: {"Model":"LLaVA-1.5"}. This record does not assert independent reproduction. ### Fox F1 Score: 86.3. Result ID: 6a4212f0fbc373592c868739. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LVLM backbone":"LLaVA-1.5"}. This record does not assert independent reproduction. ### Always-on F1 Score: 86.2. Result ID: 6a18038afbc373592c11e3c9. [Reporting paper]() Recorded evaluation configuration: {"Model":"LLaVA-1.5"}. This record does not assert independent reproduction. ### CausalMM F1 Score: 86.17. Result ID: 6a4212f0fbc373592c868737. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LVLM backbone":"LLaVA-1.5"}. This record does not assert independent reproduction. ### SID F1 Score: 85.21. Result ID: 6a4212f0fbc373592c868738. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LVLM backbone":"LLaVA-1.5"}. This record does not assert independent reproduction. ### RSP F1 Score: 85.2. Result ID: 6a18038afbc373592c11e3c1. [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. ### Always-on F1 Score: 84.2. Result ID: 6a18038afbc373592c11e3c0. [Reporting paper]() Recorded evaluation configuration: {"Model":"InstructBLIP","Prompting Strategy":"Always-on","Prompt Text":"Be careful."}. This record does not assert independent reproduction. ### ICD F1 Score: 84.18. Result ID: 6a4212f0fbc373592c868735. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LVLM backbone":"LLaVA-1.5"}. This record does not assert independent reproduction. ### Baseline F1 Score: 83.9. Result ID: 6a18038afbc373592c11e3bf. [Reporting paper]() Recorded evaluation configuration: {"Model":"InstructBLIP"}. This record does not assert independent reproduction. ### Fox F1 Score: 83.77. Result ID: 6a4212f0fbc373592c868740. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LVLM backbone":"InstructBLIP"}. This record does not assert independent reproduction. ### SID F1 Score: 83.51. Result ID: 6a4212f0fbc373592c86873f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LVLM backbone":"InstructBLIP"}. This record does not assert independent reproduction. ### Sampling F1 Score: 83.4. Result ID: 6a4212f0fbc373592c868733. [Reporting paper]() Recorded evaluation configuration: {"LVLM backbone":"LLaVA-1.5"}. This record does not assert independent reproduction. ### CausalMM F1 Score: 83.27. Result ID: 6a4212f0fbc373592c86873e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LVLM backbone":"InstructBLIP"}. This record does not assert independent reproduction. ### OPERA F1 Score: 83.21. Result ID: 6a4212f0fbc373592c868744. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"LVLM backbone":"Shikra"}. This record does not assert independent reproduction. ### OPERA F1 Score: 83.19. Result ID: 6a4212f0fbc373592c86873d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"LVLM backbone":"InstructBLIP"}. This record does not assert independent reproduction. ### CausalMM F1 Score: 82.89. Result ID: 6a4212f0fbc373592c868745. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LVLM backbone":"Shikra"}. This record does not assert independent reproduction. ### Fox F1 Score: 82.27. Result ID: 6a4212f0fbc373592c868747. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LVLM backbone":"Shikra"}. This record does not assert independent reproduction. ### VCD F1 Score: 82.05. Result ID: 6a4212f0fbc373592c868734. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LVLM backbone":"LLaVA-1.5"}. This record does not assert independent reproduction. ### ICD F1 Score: 81.74. Result ID: 6a4212f0fbc373592c86873c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LVLM backbone":"InstructBLIP"}. This record does not assert independent reproduction. ### Sampling F1 Score: 81.55. Result ID: 6a4212f0fbc373592c86873a. [Reporting paper]() Recorded evaluation configuration: {"LVLM backbone":"InstructBLIP"}. This record does not assert independent reproduction. ### VCD F1 Score: 81.12. Result ID: 6a4212f0fbc373592c86873b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LVLM backbone":"InstructBLIP"}. This record does not assert independent reproduction. ### VCD F1 Score: 81.12. Result ID: 6a4212f0fbc373592c868742. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LVLM backbone":"Shikra"}. This record does not assert independent reproduction. ### Sampling F1 Score: 81.06. Result ID: 6a4212f0fbc373592c868741. [Reporting paper]() Recorded evaluation configuration: {"LVLM backbone":"Shikra"}. This record does not assert independent reproduction. ### ICD F1 Score: 80.2. Result ID: 6a4212f0fbc373592c868743. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LVLM backbone":"Shikra"}. This record does not assert independent reproduction. ### SID F1 Score: 79.97. Result ID: 6a4212f0fbc373592c868746. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LVLM backbone":"Shikra"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.