# Open-ended Generative QA on TruthfulQA (ACC, ECE)

Source: [Open-ended Generative QA on TruthfulQA (ACC, ECE)](<https://www.sota2.com/research/sota/open-ended-generative-qa-on-truthfulqa-acc-ece>)

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

Data updated: 2026-05-15T06:56:18.905Z

Evaluation of model performance on the TruthfulQA dataset using Accuracy (ACC) and Expected Calibration Error (ECE) metrics for open-ended generative question answering.

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 | Open-ended generative Question Answering |
| Dataset (including any stated split) | TruthfulQA |
| Metric | Accuracy (ACC) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [Accuracy (ACC)](<https://www.sota2.com/research/sota/open-ended-generative-qa-on-truthfulqa-acc-ece.md?metric=Accuracy%20(ACC)>): Higher is better; unit: PERCENT.

- [Expected Calibration Error (ECE)](<https://www.sota2.com/research/sota/open-ended-generative-qa-on-truthfulqa-acc-ece.md?metric=Expected%20Calibration%20Error%20(ECE)>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Accuracy (ACC) | Result date | Report paper |
| --- | --- | --- | --- |
| UQ4CT | 94.6 | Not recorded | 68fa7ba01e209131cea896a3 |
| Verbalized Consistency | 87.49 | Not recorded | 68fa7ba01e209131cea896a3 |
| Semantic Entropy | 86.66 | Not recorded | 68fa7ba01e209131cea896a3 |
| Semantic Density | 86.66 | Not recorded | 68fa7ba01e209131cea896a3 |
| Verbalized | 85.63 | Not recorded | 68fa7ba01e209131cea896a3 |
| SeqProb | 84.19 | Not recorded | 68fa7ba01e209131cea896a3 |

### UQ4CT

Accuracy (ACC): 94.6. Result ID: 6a06c1bf47f34ce924edc571.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba01e209131cea896a3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba01e209131cea896a3.md>)

Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct","Fine-tuning":"MixLoRA","Number of samples (N)":"1","Correctness proxy":"F1-based"}. This record does not assert independent reproduction.

### Verbalized Consistency

Accuracy (ACC): 87.49. Result ID: 6a06c1bf47f34ce924edc570.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba01e209131cea896a3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72941e209131cea573ff.md>)

Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct","Fine-tuning":"MixLoRA","Number of samples (N)":"5","Correctness proxy":"F1-based"}. This record does not assert independent reproduction.

### Semantic Entropy

Accuracy (ACC): 86.66. Result ID: 6a06c1bf47f34ce924edc56c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba01e209131cea896a3.md>)

Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct","Fine-tuning":"MixLoRA","Number of samples (N)":"5","Correctness proxy":"F1-based"}. This record does not assert independent reproduction.

### Semantic Density

Accuracy (ACC): 86.66. Result ID: 6a06c1bf47f34ce924edc56d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba01e209131cea896a3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75901e209131cea68a70.md>)

Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct","Fine-tuning":"MixLoRA","Number of samples (N)":"5","Correctness proxy":"F1-based"}. This record does not assert independent reproduction.

### Verbalized

Accuracy (ACC): 85.63. Result ID: 6a06c1bf47f34ce924edc56f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba01e209131cea896a3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72941e209131cea573ff.md>)

Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct","Fine-tuning":"MixLoRA","Number of samples (N)":"1","Correctness proxy":"F1-based"}. This record does not assert independent reproduction.

### SeqProb

Accuracy (ACC): 84.19. Result ID: 6a06c1bf47f34ce924edc56e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba01e209131cea896a3.md>)

Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct","Fine-tuning":"MixLoRA","Number of samples (N)":"1","Correctness proxy":"F1-based"}. This record does not assert independent reproduction.

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