# Confidence Estimation (Iterative Tagging) on PopQA Source: [Confidence Estimation (Iterative Tagging) on PopQA]() Collection index: [llms.txt]() Data updated: 2026-05-15T07:01:08.125Z Evaluation of model confidence estimation performance on the PopQA dataset using iterative tagging methodology, measured using Brier Score (BS), Expected Calibration Error (ECE-M), and Scaled Calibration (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) | PopQA | | Metric | Brier Score | | 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](): Lower is better; unit: SCALAR. - [ECE (Mean)](): Lower is better; unit: SCALAR. - [Scaled Calibration](): Lower is better; unit: SCALAR. ## Recorded results | Method | Brier Score | Result date | Report paper | | --- | --- | --- | --- | | LOVEC-DPO | 9.6 | Not recorded | 68fa78e61e209131cea7b12b | | LOVEC-GRPO | 11.3 | Not recorded | 68fa78e61e209131cea7b12b | | LOVEC-DPO | 11.6 | Not recorded | 68fa78e61e209131cea7b12b | | LOVEC-GRPO | 13.1 | Not recorded | 68fa78e61e209131cea7b12b | | Self-Cons | 13.5 | Not recorded | 68fa78e61e209131cea7b12b | | luq | 13.6 | Not recorded | 68fa78e61e209131cea7b12b | | p(true)-ft | 14.1 | Not recorded | 68fa78e61e209131cea7b12b | | LUQ | 16.7 | Not recorded | 68fa78e61e209131cea7b12b | | Self-Cons | 17.3 | Not recorded | 68fa78e61e209131cea7b12b | | LOVEC-SFT | 18 | Not recorded | 68fa78e61e209131cea7b12b | | Verb-Conf | 18.8 | Not recorded | 68fa78e61e209131cea7b12b | | Verb-Conf | 19.5 | Not recorded | 68fa78e61e209131cea7b12b | | p(true) | 19.9 | Not recorded | 68fa78e61e209131cea7b12b | | p(true) | 21.5 | Not recorded | 68fa78e61e209131cea7b12b | | Vanilla | 21.7 | Not recorded | 68fa78e61e209131cea7b12b | | Vanilla | 24 | Not recorded | 68fa78e61e209131cea7b12b | | LOVEC-SFT | 25.8 | Not recorded | 68fa78e61e209131cea7b12b | ### LOVEC-DPO Brier Score: 9.6. Result ID: 6a06c4b047f34ce924edd319. [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: 11.3. Result ID: 6a06c4b047f34ce924edd318. [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: 11.6. Result ID: 6a06c4b047f34ce924edd341. [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: 13.1. Result ID: 6a06c4b047f34ce924edd340. [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: 13.5. Result ID: 6a06c4b047f34ce924edd33e. [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: 13.6. Result ID: 6a06c4b047f34ce924edd33a. [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: 14.1. Result ID: 6a06c4b047f34ce924edd314. [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: 16.7. Result ID: 6a06c4b047f34ce924edd311. [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: 17.3. Result ID: 6a06c4b047f34ce924edd316. [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: 18. Result ID: 6a06c4b047f34ce924edd317. [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: 18.8. Result ID: 6a06c4b047f34ce924edd315. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama3-8B-Instruct","Decoding Strategy":"Greedy"}. This record does not assert independent reproduction. ### Verb-Conf Brier Score: 19.5. Result ID: 6a06c4b047f34ce924edd33d. [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: 19.9. Result ID: 6a06c4b047f34ce924edd313. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama3-8B-Instruct","Decoding Strategy":"Greedy"}. This record does not assert independent reproduction. ### p(true) Brier Score: 21.5. Result ID: 6a06c4b047f34ce924edd33c. [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. ### Vanilla Brier Score: 21.7. Result ID: 6a06c4b047f34ce924edd312. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama3-8B-Instruct","Decoding Strategy":"Greedy"}. This record does not assert independent reproduction. ### Vanilla Brier Score: 24. Result ID: 6a06c4b047f34ce924edd33b. [Reporting 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: 25.8. Result ID: 6a06c4b047f34ce924edd33f. [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. Page 1 of 1. This is an index page, not the full collection.