# Factual Correctness on E2E Original (test)

Source: [Factual Correctness on E2E Original (test)](<https://www.sota2.com/research/sota/factual-correctness-on-e2e-original-test>)

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

Data updated: 2026-02-26T05:34:41.161Z

Evaluation of Factual Correctness performance on the test split of the E2E Original dataset, using metrics such as Add, Miss, Wrong, and SER.

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 | Factual Correctness |
| Dataset (including any stated split) | E2E Original (test) |
| Metric | Add |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 5 of 5 |
| 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

- [Add](<https://www.sota2.com/research/sota/factual-correctness-on-e2e-original-test.md?metric=Add>): Lower is better; unit: SCALAR.

- [Miss](<https://www.sota2.com/research/sota/factual-correctness-on-e2e-original-test.md?metric=Miss>): Lower is better; unit: SCALAR.

- [Wrong](<https://www.sota2.com/research/sota/factual-correctness-on-e2e-original-test.md?metric=Wrong>): Lower is better; unit: SCALAR.

- [SER](<https://www.sota2.com/research/sota/factual-correctness-on-e2e-original-test.md?metric=SER>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Add | Result date | Report paper |
| --- | --- | --- | --- |
| TGen | 0.14 | Not recorded | 68fa6a271e209131cea2665d |
| Transformer | 0.3 | Not recorded | 68fa6a271e209131cea2665d |
| AGGGEN | 0.32 | Not recorded | 68fa6a271e209131cea2665d |
| AGGGEN-OD | 1.65 | Not recorded | 68fa6a271e209131cea2665d |
| AGGGEN-AG | 8.74 | Not recorded | 68fa6a271e209131cea2665d |

### TGen

Add: 0.14. Result ID: 698e18bbffc3901de09ac530.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a271e209131cea2665d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66aa1e209131cea1182b.md>)

[Implementation](<https://github.com/tuetschek/e2e-cleaning>)

Recorded evaluation configuration: {"Source":"Previous work"}. This record does not assert independent reproduction.

### Transformer

Add: 0.3. Result ID: 698e18bbffc3901de09ac531.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a271e209131cea2665d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa703d1e209131cea49db1.md>)

[Implementation](<https://github.com/tensorflow/tensor2tensor>)

Recorded evaluation configuration: {"Implementation":"Authors' implementation"}. This record does not assert independent reproduction.

### AGGGEN

Add: 0.32. Result ID: 698e18bbffc3901de09ac532.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a271e209131cea2665d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a271e209131cea2665d.md>)

[Implementation](<https://github.com/XinnuoXu/AggGen>)

Recorded evaluation configuration: {"Input Ordering":"true","Input Aggregation":"true"}. This record does not assert independent reproduction.

### AGGGEN-OD

Add: 1.65. Result ID: 698e18bbffc3901de09ac533.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a271e209131cea2665d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a271e209131cea2665d.md>)

[Implementation](<https://github.com/XinnuoXu/AggGen>)

Recorded evaluation configuration: {"Input Ordering":"shuffled","Input Aggregation":"true"}. This record does not assert independent reproduction.

### AGGGEN-AG

Add: 8.74. Result ID: 698e18bbffc3901de09ac534.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a271e209131cea2665d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a271e209131cea2665d.md>)

[Implementation](<https://github.com/XinnuoXu/AggGen>)

Recorded evaluation configuration: {"Input Ordering":"true","Input Aggregation":"false"}. This record does not assert independent reproduction.

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