# Long-form generation factuality and uncertainty estimation on WildHallu (test) Source: [Long-form generation factuality and uncertainty estimation on WildHallu (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:45:08.637Z Evaluation of long-form generation models on the test split of the WildHallu dataset, focusing on factuality assessment and uncertainty estimation capabilities, measured via metrics like FA and #Incor. 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 | Long-form generation factuality and uncertainty estimation | | Dataset (including any stated split) | WildHallu (test) | | Metric | Factuality Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 14 of 14 | | 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 - [Factuality Score](): Higher is better; unit: PERCENT. - [Uncertainty Score](): Higher is better; unit: PERCENT. - [Incorrect Count](): Lower is better; unit: SCALAR. ## Recorded results | Method | Factuality Score | Result date | Report paper | | --- | --- | --- | --- | | LOGU-DPO | 0.86 | Not recorded | 68fa79201e209131cea7c409 | | LOGU-DPO | 0.844 | Not recorded | 68fa79201e209131cea7c409 | | Pair-Few | 0.84 | Not recorded | 68fa79201e209131cea7c409 | | Unc-Few | 0.802 | Not recorded | 68fa79201e209131cea7c409 | | LOGU-SFT | 0.792 | Not recorded | 68fa79201e209131cea7c409 | | LOGU-SFT | 0.789 | Not recorded | 68fa79201e209131cea7c409 | | Unc-Zero | 0.787 | Not recorded | 68fa79201e209131cea7c409 | | Self-Refine | 0.77 | Not recorded | 68fa79201e209131cea7c409 | | Unc-Zero | 0.754 | Not recorded | 68fa79201e209131cea7c409 | | Orig. | 0.744 | Not recorded | 68fa79201e209131cea7c409 | | Pair-Few | 0.734 | Not recorded | 68fa79201e209131cea7c409 | | Unc-Few | 0.726 | Not recorded | 68fa79201e209131cea7c409 | | Self-Refine | 0.724 | Not recorded | 68fa79201e209131cea7c409 | | Orig. | 0.715 | Not recorded | 68fa79201e209131cea7c409 | ### LOGU-DPO Factuality Score: 0.86. Result ID: 6995c80f3badfaffe6cbbfcc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Llama3-8B-Instruct","Method Category":"Training-Based"}. This record does not assert independent reproduction. ### LOGU-DPO Factuality Score: 0.844. Result ID: 6995c80f3badfaffe6cbbfc5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Mistral-7B-Instruct","Method Category":"Training-Based"}. This record does not assert independent reproduction. ### Pair-Few Factuality Score: 0.84. Result ID: 6995c80f3badfaffe6cbbfc9. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama3-8B-Instruct","Method Category":"Prompt-Based"}. This record does not assert independent reproduction. ### Unc-Few Factuality Score: 0.802. Result ID: 6995c80f3badfaffe6cbbfc8. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama3-8B-Instruct","Method Category":"Prompt-Based"}. This record does not assert independent reproduction. ### LOGU-SFT Factuality Score: 0.792. Result ID: 6995c80f3badfaffe6cbbfc4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Mistral-7B-Instruct","Method Category":"Training-Based"}. This record does not assert independent reproduction. ### LOGU-SFT Factuality Score: 0.789. Result ID: 6995c80f3badfaffe6cbbfcb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Llama3-8B-Instruct","Method Category":"Training-Based"}. This record does not assert independent reproduction. ### Unc-Zero Factuality Score: 0.787. Result ID: 6995c80f3badfaffe6cbbfc7. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama3-8B-Instruct","Method Category":"Prompt-Based"}. This record does not assert independent reproduction. ### Self-Refine Factuality Score: 0.77. Result ID: 6995c80f3badfaffe6cbbfca. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama3-8B-Instruct","Method Category":"Prompt-Based"}. This record does not assert independent reproduction. ### Unc-Zero Factuality Score: 0.754. Result ID: 6995c80f3badfaffe6cbbfc0. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Mistral-7B-Instruct","Method Category":"Prompt-Based"}. This record does not assert independent reproduction. ### Orig. Factuality Score: 0.744. Result ID: 6995c80f3badfaffe6cbbfc6. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama3-8B-Instruct","Method Category":"Original Model"}. This record does not assert independent reproduction. ### Pair-Few Factuality Score: 0.734. Result ID: 6995c80f3badfaffe6cbbfc2. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Mistral-7B-Instruct","Method Category":"Prompt-Based"}. This record does not assert independent reproduction. ### Unc-Few Factuality Score: 0.726. Result ID: 6995c80f3badfaffe6cbbfc1. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Mistral-7B-Instruct","Method Category":"Prompt-Based"}. This record does not assert independent reproduction. ### Self-Refine Factuality Score: 0.724. Result ID: 6995c80f3badfaffe6cbbfc3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Mistral-7B-Instruct","Method Category":"Prompt-Based"}. This record does not assert independent reproduction. ### Orig. Factuality Score: 0.715. Result ID: 6995c80f3badfaffe6cbbfbf. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Mistral-7B-Instruct","Method Category":"Original Model"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.