# Question Answering on SQuAD golden

Source: [Question Answering on SQuAD golden](<https://www.sota2.com/research/sota/question-answering-on-squad-golden>)

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

Data updated: 2026-02-26T05:27:02.658Z

Evaluation of model performance on the 'SQuAD golden' subset/version for 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 | Question Answering |
| Dataset (including any stated split) | SQuAD golden |
| Metric | Accuracy |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/question-answering-on-squad-golden.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| FaithfulRAG | 96.6 | Not recorded | 68fa79f01e209131cea801e8 |
| Opin (Instr) | 96 | Not recorded | 68fa79f01e209131cea801e8 |
| Origin | 95.2 | Not recorded | 68fa79f01e209131cea801e8 |
| COIECD | 95.1 | Not recorded | 68fa79f01e209131cea801e8 |
| ATTR | 94.2 | Not recorded | 68fa79f01e209131cea801e8 |
| CAD | 91.1 | Not recorded | 68fa79f01e209131cea801e8 |
| KRE | 81.4 | Not recorded | 68fa79f01e209131cea801e8 |

### FaithfulRAG

Accuracy: 96.6. Result ID: 698b66ed7a967eddb76e4db9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79f01e209131cea801e8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79f01e209131cea801e8.md>)

[Implementation](<https://github.com/DeepLearnXMU/Faithful-RAG>)

Recorded evaluation configuration: {"Backbone":"LLaMA 3.1-8B-Instruct"}. This record does not assert independent reproduction.

### Opin (Instr)

Accuracy: 96. Result ID: 698b66ed7a967eddb76e4db4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79f01e209131cea801e8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70f21e209131cea4e428.md>)

Recorded evaluation configuration: {"Backbone":"LLaMA 3.1-8B-Instruct","Method Category":"Context-faithful Prompting"}. This record does not assert independent reproduction.

### Origin

Accuracy: 95.2. Result ID: 698b66ed7a967eddb76e4db3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79f01e209131cea801e8.md>)

Recorded evaluation configuration: {"Backbone":"LLaMA 3.1-8B-Instruct"}. This record does not assert independent reproduction.

### COIECD

Accuracy: 95.1. Result ID: 698b66ed7a967eddb76e4db8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79f01e209131cea801e8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74411e209131cea608ba.md>)

[Implementation](<https://github.com/Stacy027/COIECD>)

Recorded evaluation configuration: {"Backbone":"LLaMA 3.1-8B-Instruct","Method Category":"Context-faithful Decoding"}. This record does not assert independent reproduction.

### ATTR

Accuracy: 94.2. Result ID: 698b66ed7a967eddb76e4db5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79f01e209131cea801e8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70f21e209131cea4e428.md>)

Recorded evaluation configuration: {"Backbone":"LLaMA 3.1-8B-Instruct","Method Category":"Context-faithful Prompting"}. This record does not assert independent reproduction.

### CAD

Accuracy: 91.1. Result ID: 698b66ed7a967eddb76e4db7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79f01e209131cea801e8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f6e1e209131cea45813.md>)

Recorded evaluation configuration: {"Backbone":"LLaMA 3.1-8B-Instruct","Method Category":"Context-faithful Decoding"}. This record does not assert independent reproduction.

### KRE

Accuracy: 81.4. Result ID: 698b66ed7a967eddb76e4db6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79f01e209131cea801e8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72451e209131cea556ce.md>)

Recorded evaluation configuration: {"Backbone":"LLaMA 3.1-8B-Instruct","Method Category":"Context-faithful Prompting"}. This record does not assert independent reproduction.

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