# Confidence Estimation (Iterative Tagging) on Bios Source: [Confidence Estimation (Iterative Tagging) on Bios]() Collection index: [llms.txt]() Data updated: 2026-05-15T07:01:08.092Z Evaluation of model confidence estimation performance on the Bios dataset using iterative tagging methodology, reporting metrics like BS, ECE-M, and SC. 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 | Confidence Estimation (Iterative Tagging) | | Dataset (including any stated split) | Bios | | Metric | Brier Score (BS) | | Unit | SCALAR | | Direction | Lower is better | | Results loaded | 17 of 17 | | 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 - [Brier Score (BS)](): Lower is better; unit: SCALAR. - [Expected Calibration Error (ECE-M)](): Lower is better; unit: PERCENT. - [Score Calibration (SC)](): Higher is better; unit: SCALAR. ## Recorded results | Method | Brier Score (BS) | Result date | Report paper | | --- | --- | --- | --- | | LOVEC-DPO | 7.5 | Not recorded | 68fa78e61e209131cea7b12b | | LOVEC-GRPO | 8.5 | Not recorded | 68fa78e61e209131cea7b12b | | LOVEC-DPO | 9 | Not recorded | 68fa78e61e209131cea7b12b | | LOVEC-GRPO | 10.7 | Not recorded | 68fa78e61e209131cea7b12b | | luq | 12.2 | Not recorded | 68fa78e61e209131cea7b12b | | Self-Cons | 13 | Not recorded | 68fa78e61e209131cea7b12b | | p(true)-ft | 15.2 | Not recorded | 68fa78e61e209131cea7b12b | | LOVEC-SFT | 16.6 | Not recorded | 68fa78e61e209131cea7b12b | | Verb-Conf | 18 | Not recorded | 68fa78e61e209131cea7b12b | | LOVEC-SFT | 18.8 | Not recorded | 68fa78e61e209131cea7b12b | | p(true) | 19.7 | Not recorded | 68fa78e61e209131cea7b12b | | LUQ | 20 | Not recorded | 68fa78e61e209131cea7b12b | | Self-Cons | 20.3 | Not recorded | 68fa78e61e209131cea7b12b | | Vanilla | 20.9 | Not recorded | 68fa78e61e209131cea7b12b | | p(true) | 21 | Not recorded | 68fa78e61e209131cea7b12b | | Verb-Conf | 21.2 | Not recorded | 68fa78e61e209131cea7b12b | | Vanilla | 24.5 | Not recorded | 68fa78e61e209131cea7b12b | ### LOVEC-DPO Brier Score (BS): 7.5. Result ID: 6a06c4b047f34ce924edd339. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Gemma-2-9B-It","Tagging Strategy":"Sentence-level iterative tagging"}. This record does not assert independent reproduction. ### LOVEC-GRPO Brier Score (BS): 8.5. Result ID: 6a06c4b047f34ce924edd30f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Tagging Format":"Iterative","Backbone":"Llama3-8B-Instruct","Decoding Strategy":"Greedy"}. This record does not assert independent reproduction. ### LOVEC-DPO Brier Score (BS): 9. Result ID: 6a06c4b047f34ce924edd310. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Tagging Format":"Iterative","Backbone":"Llama3-8B-Instruct","Decoding Strategy":"Greedy"}. This record does not assert independent reproduction. ### LOVEC-GRPO Brier Score (BS): 10.7. Result ID: 6a06c4b047f34ce924edd338. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Gemma-2-9B-It","Tagging Strategy":"Sentence-level iterative tagging"}. This record does not assert independent reproduction. ### luq Brier Score (BS): 12.2. Result ID: 6a06c4b047f34ce924edd332. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Gemma-2-9B-It","Tagging Strategy":"Sentence-level iterative tagging"}. This record does not assert independent reproduction. ### Self-Cons Brier Score (BS): 13. Result ID: 6a06c4b047f34ce924edd336. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Gemma-2-9B-It","Tagging Strategy":"Sentence-level iterative tagging"}. This record does not assert independent reproduction. ### p(true)-ft Brier Score (BS): 15.2. Result ID: 6a06c4b047f34ce924edd30b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama3-8B-Instruct","Decoding Strategy":"Greedy"}. This record does not assert independent reproduction. ### LOVEC-SFT Brier Score (BS): 16.6. Result ID: 6a06c4b047f34ce924edd30e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Tagging Format":"Iterative","Backbone":"Llama3-8B-Instruct","Decoding Strategy":"Greedy"}. This record does not assert independent reproduction. ### Verb-Conf Brier Score (BS): 18. Result ID: 6a06c4b047f34ce924edd335. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Gemma-2-9B-It","Tagging Strategy":"Sentence-level iterative tagging"}. This record does not assert independent reproduction. ### LOVEC-SFT Brier Score (BS): 18.8. Result ID: 6a06c4b047f34ce924edd337. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Gemma-2-9B-It","Tagging Strategy":"Sentence-level iterative tagging"}. This record does not assert independent reproduction. ### p(true) Brier Score (BS): 19.7. Result ID: 6a06c4b047f34ce924edd30a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama3-8B-Instruct","Decoding Strategy":"Greedy"}. This record does not assert independent reproduction. ### LUQ Brier Score (BS): 20. Result ID: 6a06c4b047f34ce924edd308. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama3-8B-Instruct","Decoding Strategy":"Greedy"}. This record does not assert independent reproduction. ### Self-Cons Brier Score (BS): 20.3. Result ID: 6a06c4b047f34ce924edd30d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama3-8B-Instruct","Decoding Strategy":"Greedy"}. This record does not assert independent reproduction. ### Vanilla Brier Score (BS): 20.9. Result ID: 6a06c4b047f34ce924edd309. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama3-8B-Instruct","Decoding Strategy":"Greedy"}. This record does not assert independent reproduction. ### p(true) Brier Score (BS): 21. Result ID: 6a06c4b047f34ce924edd334. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Gemma-2-9B-It","Tagging Strategy":"Sentence-level iterative tagging"}. This record does not assert independent reproduction. ### Verb-Conf Brier Score (BS): 21.2. Result ID: 6a06c4b047f34ce924edd30c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama3-8B-Instruct","Decoding Strategy":"Greedy"}. This record does not assert independent reproduction. ### Vanilla Brier Score (BS): 24.5. Result ID: 6a06c4b047f34ce924edd333. [Reporting paper]() Recorded evaluation configuration: {"Base Model":"Gemma-2-9B-It","Tagging Strategy":"Sentence-level iterative tagging"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.