# Information Extraction on Campaign-finance filings

Source: [Information Extraction on Campaign-finance filings](<https://www.sota2.com/research/sota/information-extraction-on-campaign-finance-filings>)

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

Data updated: 2026-04-13T09:57:00.562Z

Evaluation of Information Extraction performance on the Campaign-finance filings dataset, measured by Mean per field accuracy.

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 | Information extraction |
| Dataset (including any stated split) | Campaign-finance filings |
| Metric | Mean per field Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [Mean per field Accuracy](<https://www.sota2.com/research/sota/information-extraction-on-campaign-finance-filings.md?metric=Mean%20per%20field%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Mean per field Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Fine-tuning | 98.71 | Not recorded | 69dc78a17d0172140ec78beb |
| KNN | 55.12 | Not recorded | 69dc78a17d0172140ec78beb |
| DSPy GEPA | 53.21 | Not recorded | 69dc78a17d0172140ec78beb |
| DSPy BootstrapFewShot (#12) | 42.95 | Not recorded | 69dc78a17d0172140ec78beb |
| DSPy MIPROv2 | 42.31 | Not recorded | 69dc78a17d0172140ec78beb |
| Initial prompt | 36.54 | Not recorded | 69dc78a17d0172140ec78beb |
| AIR | 35.9 | Not recorded | 69dc78a17d0172140ec78beb |
| TextGrad | 25.64 | Not recorded | 69dc78a17d0172140ec78beb |

### Fine-tuning

Mean per field Accuracy: 98.71. Result ID: 69dcbdd547f34ce924c4203b.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78a17d0172140ec78beb.md>)

Recorded evaluation configuration: {"Train Tokens (Base Model)":"502968 / 11178","Inference Tokens (Base Model)":"62099 / 1377"}. This record does not assert independent reproduction.

### KNN

Mean per field Accuracy: 55.12. Result ID: 69dcbdd547f34ce924c4203a.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78a17d0172140ec78beb.md>)

Recorded evaluation configuration: {"Inference Tokens (Base Model)":"219450 / 1371"}. This record does not assert independent reproduction.

### DSPy GEPA

Mean per field Accuracy: 53.21. Result ID: 69dcbdd547f34ce924c4203e.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78a17d0172140ec78beb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a3a1e209131cea81ee3.md>)

Recorded evaluation configuration: {"Train Tokens (Base Model)":"2142493 / 20824","Train Tokens (Reflection Model)":"206378 / 91251","Inference Tokens (Base Model)":"265211 / 1847"}. This record does not assert independent reproduction.

### DSPy BootstrapFewShot (#12)

Mean per field Accuracy: 42.95. Result ID: 69dcbdd547f34ce924c4203c.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78a17d0172140ec78beb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70d01e209131cea4d60e.md>)

[Implementation](<https://github.com/stanfordnlp/dspy>)

Recorded evaluation configuration: {"Train Tokens (Base Model)":"55479 / 144","Inference Tokens (Base Model)":"736331 / 1829"}. This record does not assert independent reproduction.

### DSPy MIPROv2

Mean per field Accuracy: 42.31. Result ID: 69dcbdd547f34ce924c4203d.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78a17d0172140ec78beb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75121e209131cea65828.md>)

Recorded evaluation configuration: {"Train Tokens (Base Model)":"6399076 / 40216","Inference Tokens (Base Model)":"358187 / 1838"}. This record does not assert independent reproduction.

### Initial prompt

Mean per field Accuracy: 36.54. Result ID: 69dcbdd547f34ce924c42039.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78a17d0172140ec78beb.md>)

Recorded evaluation configuration: {"Inference Tokens (Base Model)":"62099 / 1651"}. This record does not assert independent reproduction.

### AIR

Mean per field Accuracy: 35.9. Result ID: 69dcbdd547f34ce924c42040.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78a17d0172140ec78beb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69dc78a17d0172140ec78beb.md>)

Recorded evaluation configuration: {"Train Tokens (Embed Model)":"200111 / -","Train Tokens (Base Model)":"176632 / 3559","Train Tokens (Reflection Model)":"102743 / 52487","Inference Tokens (Base Model)":"172235 / 1658"}. This record does not assert independent reproduction.

### TextGrad

Mean per field Accuracy: 25.64. Result ID: 69dcbdd547f34ce924c4203f.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78a17d0172140ec78beb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73981e209131cea5d7cd.md>)

[Implementation](<https://github.com/zou-group/textgrad>)

Recorded evaluation configuration: {"Train Tokens (Base Model)":"284301 / 1723","Train Tokens (Reflection Model)":"218746 / 194031","Inference Tokens (Base Model)":"187991 / 1404"}. This record does not assert independent reproduction.

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