# Open-ended Generation on TruthfulQA single info 1.0 (test)

Source: [Open-ended Generation on TruthfulQA single info 1.0 (test)](<https://www.sota2.com/research/sota/open-ended-generation-on-truthfulqa-single-info-1-0-test>)

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

Data updated: 2026-02-26T06:07:44.304Z

Evaluation of model performance on the specific 'single info 1.0 (test)' split of the TruthfulQA dataset, measuring metrics related to truthfulness ('True') and combined truthfulness/informativeness ('True\*Info').

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 generation |
| Dataset (including any stated split) | TruthfulQA single info 1.0 (test) |
| Metric | Truthfulness Score |
| 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

- [Truthfulness Score](<https://www.sota2.com/research/sota/open-ended-generation-on-truthfulqa-single-info-1-0-test.md?metric=Truthfulness%20Score>): Higher is better; unit: PERCENT.

- [Truthfulness \* Informativeness Score](<https://www.sota2.com/research/sota/open-ended-generation-on-truthfulqa-single-info-1-0-test.md?metric=Truthfulness%20*%20Informativeness%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Truthfulness Score | Result date | Report paper |
| --- | --- | --- | --- |
| TACS-T | 66.6 | Not recorded | 68fa74ce1e209131cea63ff7 |
| TACS-S | 61.8 | Not recorded | 68fa74ce1e209131cea63ff7 |
| Mistral-Instruct-v0.2 | 59.9 | Not recorded | 68fa74ce1e209131cea63ff7 |
| TACS-S | 59.4 | Not recorded | 68fa74ce1e209131cea63ff7 |
| TACS-T | 56.9 | Not recorded | 68fa74ce1e209131cea63ff7 |
| Llama 2-Chat | 55.1 | Not recorded | 68fa74ce1e209131cea63ff7 |
| ITI | 53.2 | Not recorded | 68fa74ce1e209131cea63ff7 |

### TACS-T

Truthfulness Score: 66.6. Result ID: 69937c2e3a6c3148491646c2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74ce1e209131cea63ff7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74ce1e209131cea63ff7.md>)

[Implementation](<https://github.com/ictnlp/TACS>)

Recorded evaluation configuration: {"Backbone":"Mistral-Instruct-v0.2","Selection Strategy":"Token-level Truth-Aware Context Selection"}. This record does not assert independent reproduction.

### TACS-S

Truthfulness Score: 61.8. Result ID: 69937c2e3a6c3148491646c3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74ce1e209131cea63ff7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74ce1e209131cea63ff7.md>)

[Implementation](<https://github.com/ictnlp/TACS>)

Recorded evaluation configuration: {"Backbone":"Mistral-Instruct-v0.2","Selection Strategy":"Sentence-level Truth-Aware Context Selection"}. This record does not assert independent reproduction.

### Mistral-Instruct-v0.2

Truthfulness Score: 59.9. Result ID: 69937c2e3a6c3148491646c1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74ce1e209131cea63ff7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70d61e209131cea4d909.md>)

[Implementation](<https://github.com/mistralai/mistral-src>)

Recorded evaluation configuration: {"Backbone":"Mistral-Instruct-v0.2","Selection Strategy":"Baseline"}. This record does not assert independent reproduction.

### TACS-S

Truthfulness Score: 59.4. Result ID: 69937c2e3a6c3148491646c0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74ce1e209131cea63ff7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74ce1e209131cea63ff7.md>)

[Implementation](<https://github.com/ictnlp/TACS>)

Recorded evaluation configuration: {"Backbone":"Llama 2-Chat","Selection Strategy":"Sentence-level Truth-Aware Context Selection"}. This record does not assert independent reproduction.

### TACS-T

Truthfulness Score: 56.9. Result ID: 69937c2e3a6c3148491646bf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74ce1e209131cea63ff7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74ce1e209131cea63ff7.md>)

[Implementation](<https://github.com/ictnlp/TACS>)

Recorded evaluation configuration: {"Backbone":"Llama 2-Chat","Selection Strategy":"Token-level Truth-Aware Context Selection"}. This record does not assert independent reproduction.

### Llama 2-Chat

Truthfulness Score: 55.1. Result ID: 69937c2e3a6c3148491646bd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74ce1e209131cea63ff7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa701f1e209131cea492fe.md>)

[Implementation](<https://github.com/facebookresearch/llama>)

Recorded evaluation configuration: {"Backbone":"Llama 2-Chat","Selection Strategy":"Baseline"}. This record does not assert independent reproduction.

### ITI

Truthfulness Score: 53.2. Result ID: 69937c2e3a6c3148491646be.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74ce1e209131cea63ff7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73e31e209131cea5eb16.md>)

Recorded evaluation configuration: {"Backbone":"Llama 2-Chat","Selection Strategy":"Inference-Time Intervention"}. This record does not assert independent reproduction.

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