# Knowledge-intensive Question Answering on MuSiQue (Truthfulness, Hallucination, Accuracy)

Source: [Knowledge-intensive Question Answering on MuSiQue (Truthfulness, Hallucination, Accuracy)](<https://www.sota2.com/research/sota/knowledge-intensive-question-answering-on-musique-truthfulness-hallucination-accuracy>)

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

Data updated: 2026-06-11T06:34:50.783Z

Evaluation of model performance on the MuSiQue dataset for Knowledge-intensive Question Answering, measured using Truthfulness, Hallucination, and Accuracy metrics.

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 | Knowledge-intensive Question Answering |
| Dataset (including any stated split) | MuSiQue |
| Metric | Truthfulness Score (T) |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 2 of 2 |
| 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 (T)](<https://www.sota2.com/research/sota/knowledge-intensive-question-answering-on-musique-truthfulness-hallucination-accuracy.md?metric=Truthfulness%20Score%20(T)>): Higher is better; unit: SCALAR.

- [Hallucination Rate (H)](<https://www.sota2.com/research/sota/knowledge-intensive-question-answering-on-musique-truthfulness-hallucination-accuracy.md?metric=Hallucination%20Rate%20(H)>): Lower is better; unit: SCALAR.

- [Accuracy (A)](<https://www.sota2.com/research/sota/knowledge-intensive-question-answering-on-musique-truthfulness-hallucination-accuracy.md?metric=Accuracy%20(A)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Truthfulness Score (T) | Result date | Report paper |
| --- | --- | --- | --- |
| TruthRL | -0.9 | Not recorded | 68fa7bc81e209131cea8a72b |
| TruthRL | -1.7 | Not recorded | 68fa7bc81e209131cea8a72b |

### TruthRL

Truthfulness Score (T): -0.9. Result ID: 6a2a55ccfbc373592c26b32d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc81e209131cea8a72b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bc81e209131cea8a72b.md>)

Recorded evaluation configuration: {"Retrieval Setting":"With Retrieval","Backbone":"Llama3.1-8B-Inst"}. This record does not assert independent reproduction.

### TruthRL

Truthfulness Score (T): -1.7. Result ID: 6a2a55ccfbc373592c26b32c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc81e209131cea8a72b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bc81e209131cea8a72b.md>)

Recorded evaluation configuration: {"Retrieval Setting":"Without Retrieval","Backbone":"Qwen2.5-7B-Inst"}. This record does not assert independent reproduction.

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