# Short-form Question Answering on Trivia QA

Source: [Short-form Question Answering on Trivia QA](<https://www.sota2.com/research/sota/short-form-question-answering-on-trivia-qa>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-05-15T07:01:08.216Z

Evaluation of model performance on the Trivia QA dataset for Short-form Question Answering, reporting AUROC and Expected Calibration Error (ECE).

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 | Short-form Question Answering |
| Dataset (including any stated split) | Trivia QA |
| Metric | AUROC |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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

- [AUROC](<https://www.sota2.com/research/sota/short-form-question-answering-on-trivia-qa.md?metric=AUROC>): Higher is better; unit: PERCENT.

- [ECE](<https://www.sota2.com/research/sota/short-form-question-answering-on-trivia-qa.md?metric=ECE>): Lower is better; unit: PERCENT.

## Recorded results

| Method | AUROC | Result date | Report paper |
| --- | --- | --- | --- |
| Rewarding Doubt\* | 85.9 | Not recorded | 68fa78e61e209131cea7b12b |
| Self-Cons | 73.4 | Not recorded | 68fa78e61e209131cea7b12b |
| LOVEC-DPO | 71.2 | Not recorded | 68fa78e61e209131cea7b12b |
| LOVEC-GRPO | 69.2 | Not recorded | 68fa78e61e209131cea7b12b |
| p(true) | 60.1 | Not recorded | 68fa78e61e209131cea7b12b |
| LOVEC-SFT | 56.3 | Not recorded | 68fa78e61e209131cea7b12b |
| Self-Verb | 50 | Not recorded | 68fa78e61e209131cea7b12b |

### Rewarding Doubt\*

AUROC: 85.9. Result ID: 6a06c4b047f34ce924edd326.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78e61e209131cea7b12b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78b41e209131cea79e3f.md>)

Recorded evaluation configuration: {"Category":"Literature SOTA"}. This record does not assert independent reproduction.

### Self-Cons

AUROC: 73.4. Result ID: 6a06c4b047f34ce924edd325.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78e61e209131cea7b12b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70d71e209131cea4d943.md>)

Recorded evaluation configuration: {"Category":"Baselines"}. This record does not assert independent reproduction.

### LOVEC-DPO

AUROC: 71.2. Result ID: 6a06c4b047f34ce924edd329.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78e61e209131cea7b12b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78e61e209131cea7b12b.md>)

Recorded evaluation configuration: {"Category":"Our Methods"}. This record does not assert independent reproduction.

### LOVEC-GRPO

AUROC: 69.2. Result ID: 6a06c4b047f34ce924edd328.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78e61e209131cea7b12b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78e61e209131cea7b12b.md>)

Recorded evaluation configuration: {"Category":"Our Methods"}. This record does not assert independent reproduction.

### p(true)

AUROC: 60.1. Result ID: 6a06c4b047f34ce924edd324.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78e61e209131cea7b12b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6df71e209131cea3d034.md>)

Recorded evaluation configuration: {"Category":"Baselines"}. This record does not assert independent reproduction.

### LOVEC-SFT

AUROC: 56.3. Result ID: 6a06c4b047f34ce924edd327.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78e61e209131cea7b12b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78e61e209131cea7b12b.md>)

Recorded evaluation configuration: {"Category":"Our Methods"}. This record does not assert independent reproduction.

### Self-Verb

AUROC: 50. Result ID: 6a06c4b047f34ce924edd323.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78e61e209131cea7b12b.md>)

Recorded evaluation configuration: {"Category":"Baselines"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.