SQuAD (Utility Accuracy)
SQuAD (Utility Accuracy) - answer/utility accuracy on the SQuAD grounding setup as run in the AA eval-framework on the Kolibri card.
Category
Grounding Hallucination
Score type
percent
Scale
100%
higher is better
Models tested
1
What is SQuAD (Utility Accuracy)?
SQuAD (Utility Accuracy) is a benchmark for whether answers stay grounded in provided sources. The official description says: "SQuAD (Utility Accuracy) - answer/utility accuracy on the SQuAD grounding setup as run in the AA eval-framework on the Kolibri card". Below we describe in simple words what benchmarks of this type generally examine.
What does it test?
SQuAD (Utility Accuracy) measures whether answers stay grounded in provided sources. In detail, it checks:
- answering only from the given documents instead of inventing facts
- admitting when the source does not contain the answer
- correcting or flagging false statements in the source material
- distinguishing between supported claims and plausible guesses
How to read the score
The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better.
Official methodology note: SQuAD (Utility Accuracy) - answer/utility accuracy on the SQuAD grounding setup as run in the AA eval-framework on the Kolibri card.
Frequently asked questions
What is the SQuAD (Utility Accuracy) benchmark?
SQuAD (Utility Accuracy) is a benchmark for whether answers stay grounded in provided sources. The official description says: 'SQuAD (Utility Accuracy) - answer/utility accuracy on the SQuAD grounding setup as run in the AA eval-framework on the Kolibri card'. Below we describe in simple words what benchmarks of this type generally examine.
What does SQuAD (Utility Accuracy) test?
SQuAD (Utility Accuracy) mainly measures whether answers stay grounded in provided sources. Concretely, it checks: answering only from the given documents instead of inventing facts; admitting when the source does not contain the answer; correcting or flagging false statements in the source material.
How is the SQuAD (Utility Accuracy) score calculated?
The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better. The declared maximum score of this benchmark is 100.0.
Where do I get SQuAD (Utility Accuracy) data and scores?
The official benchmark page/reference is linked on this page. Every score on Open LLM Radar is also available as open data: download the scores JSON (http://open-llm-radar-api:8000/api/v1/benchmarks/squad-utility-accuracy/scores) or pull it directly from the Open LLM Radar API with any HTTP client.
Benchmark data & downloads
Where to get, inspect and reuse the data behind this benchmark.