# Factuality and Uncertainty Estimation on Bios (test) Source: [Factuality and Uncertainty Estimation on Bios (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:44:01.190Z Evaluation of long-form generation models on the test split of the Bios 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) | Bios (test) | | Metric | FA | | 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 - [FA](): Higher is better; unit: PERCENT. - [UA](): Higher is better; unit: SCALAR. - [Incor Count](): Lower is better; unit: PERCENT. ## Recorded results | Method | FA | Result date | Report paper | | --- | --- | --- | --- | | LOGU-DPO | 71.4 | Not recorded | 68fa79201e209131cea7c409 | | LOGU-DPO | 65.4 | Not recorded | 68fa79201e209131cea7c409 | | Pair-Few | 60.6 | Not recorded | 68fa79201e209131cea7c409 | | Unc-Few | 58.7 | Not recorded | 68fa79201e209131cea7c409 | | LOGU-SFT | 58.5 | Not recorded | 68fa79201e209131cea7c409 | | LOGU-SFT | 54.5 | Not recorded | 68fa79201e209131cea7c409 | | Unc-Zero | 53.8 | Not recorded | 68fa79201e209131cea7c409 | | Orig. | 51.9 | Not recorded | 68fa79201e209131cea7c409 | | Self-Refine | 51.8 | Not recorded | 68fa79201e209131cea7c409 | | Unc-Zero | 43.6 | Not recorded | 68fa79201e209131cea7c409 | | Unc-Few | 41.7 | Not recorded | 68fa79201e209131cea7c409 | | Pair-Few | 40.3 | Not recorded | 68fa79201e209131cea7c409 | | Orig. | 38.8 | Not recorded | 68fa79201e209131cea7c409 | | Self-Refine | 38.3 | Not recorded | 68fa79201e209131cea7c409 | ### LOGU-DPO FA: 71.4. Result ID: 6995c80f3badfaffe6cbbfb0. [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 FA: 65.4. Result ID: 6995c80f3badfaffe6cbbfa9. [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 FA: 60.6. Result ID: 6995c80f3badfaffe6cbbfad. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama3-8B-Instruct","Method Category":"Prompt-Based"}. This record does not assert independent reproduction. ### Unc-Few FA: 58.7. Result ID: 6995c80f3badfaffe6cbbfac. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama3-8B-Instruct","Method Category":"Prompt-Based"}. This record does not assert independent reproduction. ### LOGU-SFT FA: 58.5. Result ID: 6995c80f3badfaffe6cbbfaf. [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-SFT FA: 54.5. Result ID: 6995c80f3badfaffe6cbbfa8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Mistral-7B-Instruct","Method Category":"Training-Based"}. This record does not assert independent reproduction. ### Unc-Zero FA: 53.8. Result ID: 6995c80f3badfaffe6cbbfab. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama3-8B-Instruct","Method Category":"Prompt-Based"}. This record does not assert independent reproduction. ### Orig. FA: 51.9. Result ID: 6995c80f3badfaffe6cbbfaa. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama3-8B-Instruct","Method Category":"Original Model"}. This record does not assert independent reproduction. ### Self-Refine FA: 51.8. Result ID: 6995c80f3badfaffe6cbbfae. [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 FA: 43.6. Result ID: 6995c80f3badfaffe6cbbfa4. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Mistral-7B-Instruct","Method Category":"Prompt-Based"}. This record does not assert independent reproduction. ### Unc-Few FA: 41.7. Result ID: 6995c80f3badfaffe6cbbfa5. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Mistral-7B-Instruct","Method Category":"Prompt-Based"}. This record does not assert independent reproduction. ### Pair-Few FA: 40.3. Result ID: 6995c80f3badfaffe6cbbfa6. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Mistral-7B-Instruct","Method Category":"Prompt-Based"}. This record does not assert independent reproduction. ### Orig. FA: 38.8. Result ID: 6995c80f3badfaffe6cbbfa3. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Mistral-7B-Instruct","Method Category":"Original Model"}. This record does not assert independent reproduction. ### Self-Refine FA: 38.3. Result ID: 6995c80f3badfaffe6cbbfa7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Mistral-7B-Instruct","Method Category":"Prompt-Based"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.