# Probabilistic Multiple-Choice on TruthfulQA (single info)

Source: [Probabilistic Multiple-Choice on TruthfulQA (single info)](<https://www.sota2.com/research/sota/probabilistic-multiple-choice-on-truthfulqa-single-info>)

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

Data updated: 2026-02-26T05:49:44.273Z

Evaluation of model performance on the TruthfulQA dataset using probabilistic multiple-choice metrics (MC1, MC2, MC3).

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 | Probabilistic Multiple-Choice |
| Dataset (including any stated split) | TruthfulQA single info |
| Metric | MC1 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

- [MC1 Score](<https://www.sota2.com/research/sota/probabilistic-multiple-choice-on-truthfulqa-single-info.md?metric=MC1%20Score>): Higher is better; unit: PERCENT.

- [MC2 Score](<https://www.sota2.com/research/sota/probabilistic-multiple-choice-on-truthfulqa-single-info.md?metric=MC2%20Score>): Higher is better; unit: PERCENT.

- [MC3 Score](<https://www.sota2.com/research/sota/probabilistic-multiple-choice-on-truthfulqa-single-info.md?metric=MC3%20Score>): Higher is better; unit: PERCENT.

- [Average Score](<https://www.sota2.com/research/sota/probabilistic-multiple-choice-on-truthfulqa-single-info.md?metric=Average%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | MC1 Score | Result date | Report paper |
| --- | --- | --- | --- |
| Mistral-Instruct-v0.2 + TACS-T | 59.2 | Not recorded | 68fa74ce1e209131cea63ff7 |
| Mistral-Instruct-v0.2 + TACS-S | 55.8 | Not recorded | 68fa74ce1e209131cea63ff7 |
| Mistral-Instruct-v0.2 | 53.6 | Not recorded | 68fa74ce1e209131cea63ff7 |
| Llama 2-Chat + TACS-S | 50.8 | Not recorded | 68fa74ce1e209131cea63ff7 |
| Llama 2-Chat | 50.6 | Not recorded | 68fa74ce1e209131cea63ff7 |
| Llama 2-Chat + ITI | 50.6 | Not recorded | 68fa74ce1e209131cea63ff7 |
| Llama 2-Chat + TACS-T | 48.8 | Not recorded | 68fa74ce1e209131cea63ff7 |

### Mistral-Instruct-v0.2 + TACS-T

MC1 Score: 59.2. Result ID: 69937c2e3a6c3148491646b4.

[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","Granularity":"token-level (TACS-T)"}. This record does not assert independent reproduction.

### Mistral-Instruct-v0.2 + TACS-S

MC1 Score: 55.8. Result ID: 69937c2e3a6c3148491646b5.

[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","Granularity":"sentence-level (TACS-S)"}. This record does not assert independent reproduction.

### Mistral-Instruct-v0.2

MC1 Score: 53.6. Result ID: 69937c2e3a6c3148491646b3.

[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"}. This record does not assert independent reproduction.

### Llama 2-Chat + TACS-S

MC1 Score: 50.8. Result ID: 69937c2e3a6c3148491646b2.

[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","Granularity":"sentence-level (TACS-S)"}. This record does not assert independent reproduction.

### Llama 2-Chat

MC1 Score: 50.6. Result ID: 69937c2e3a6c3148491646af.

[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"}. This record does not assert independent reproduction.

### Llama 2-Chat + ITI

MC1 Score: 50.6. Result ID: 69937c2e3a6c3148491646b0.

[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","Enhancement":"ITI"}. This record does not assert independent reproduction.

### Llama 2-Chat + TACS-T

MC1 Score: 48.8. Result ID: 69937c2e3a6c3148491646b1.

[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","Granularity":"token-level (TACS-T)"}. This record does not assert independent reproduction.

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