# Section Identification on MedSecId Corpus

Source: [Section Identification on MedSecId Corpus](<https://www.sota2.com/research/sota/section-identification-on-medsecid-corpus>)

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

Data updated: 2026-02-26T05:29:37.700Z

Evaluation of Section Identification performance on the MedSecId Corpus dataset, reporting standard classification metrics like Accuracy, Precision, Recall, F1, and Exact Match (EM).

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 | Section Identification |
| Dataset (including any stated split) | MedSecId Corpus |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 16 of 16 |
| 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/section-identification-on-medsecid-corpus.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Precision](<https://www.sota2.com/research/sota/section-identification-on-medsecid-corpus.md?metric=Precision>): Higher is better; unit: PERCENT.

- [Recall](<https://www.sota2.com/research/sota/section-identification-on-medsecid-corpus.md?metric=Recall>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/section-identification-on-medsecid-corpus.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

- [EM](<https://www.sota2.com/research/sota/section-identification-on-medsecid-corpus.md?metric=EM>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| GPT-4 | 96.86 | Not recorded | 68fa72f91e209131cea59aca |
| GPT-4 | 94.9 | Not recorded | 68fa72f91e209131cea59aca |
| GPT-4 | 94.41 | Not recorded | 68fa72f91e209131cea59aca |
| BILSTM-CRF | 82.2 | Not recorded | 68fa72f91e209131cea59aca |
| GPT-4 | 73.23 | Not recorded | 68fa72f91e209131cea59aca |
| MedSpacy | 56.63 | Not recorded | 68fa72f91e209131cea59aca |
| LLaMa-2 | 52.29 | Not recorded | 68fa72f91e209131cea59aca |
| Regex | 49.24 | Not recorded | 68fa72f91e209131cea59aca |
| LLaMa-2 | 39.96 | Not recorded | 68fa72f91e209131cea59aca |
| LLaMa-2 | 38.21 | Not recorded | 68fa72f91e209131cea59aca |
| Keyword Based | 36.07 | Not recorded | 68fa72f91e209131cea59aca |
| LLaMa-2 | 13.95 | Not recorded | 68fa72f91e209131cea59aca |
| Mistral | 11.99 | Not recorded | 68fa72f91e209131cea59aca |
| Mistral | 11.51 | Not recorded | 68fa72f91e209131cea59aca |
| Mistral | 8.41 | Not recorded | 68fa72f91e209131cea59aca |
| Mistral | 5.24 | Not recorded | 68fa72f91e209131cea59aca |

### GPT-4

Accuracy: 96.86. Result ID: 6992a6043a6c314849106386.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72f91e209131cea59aca.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72f91e209131cea59aca.md>)

[Implementation](<https://github.com/inQbator-eviCore/LLM_section_identifiers>)

Recorded evaluation configuration: {"Prompting Strategy":"One Shot Prompt"}. This record does not assert independent reproduction.

### GPT-4

Accuracy: 94.9. Result ID: 6992a6043a6c314849106384.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72f91e209131cea59aca.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72f91e209131cea59aca.md>)

[Implementation](<https://github.com/inQbator-eviCore/LLM_section_identifiers>)

Recorded evaluation configuration: {"Prompting Strategy":"Chain-of-Thought (COT)"}. This record does not assert independent reproduction.

### GPT-4

Accuracy: 94.41. Result ID: 6992a6043a6c314849106385.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72f91e209131cea59aca.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72f91e209131cea59aca.md>)

[Implementation](<https://github.com/inQbator-eviCore/LLM_section_identifiers>)

Recorded evaluation configuration: {"Prompting Strategy":"Zero Shot Prompt"}. This record does not assert independent reproduction.

### BILSTM-CRF

Accuracy: 82.2. Result ID: 6992a6043a6c31484910638f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72f91e209131cea59aca.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### GPT-4

Accuracy: 73.23. Result ID: 6992a6043a6c314849106383.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72f91e209131cea59aca.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72f91e209131cea59aca.md>)

[Implementation](<https://github.com/inQbator-eviCore/LLM_section_identifiers>)

Recorded evaluation configuration: {"Prompting Strategy":"Close Ended Prompt"}. This record does not assert independent reproduction.

### MedSpacy

Accuracy: 56.63. Result ID: 6992a6043a6c314849106382.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72f91e209131cea59aca.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a2c1e209131cea26947.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### LLaMa-2

Accuracy: 52.29. Result ID: 6992a6043a6c314849106388.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72f91e209131cea59aca.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72f91e209131cea59aca.md>)

[Implementation](<https://github.com/inQbator-eviCore/LLM_section_identifiers>)

Recorded evaluation configuration: {"Prompting Strategy":"Zero Shot Prompt"}. This record does not assert independent reproduction.

### Regex

Accuracy: 49.24. Result ID: 6992a6043a6c314849106381.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72f91e209131cea59aca.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### LLaMa-2

Accuracy: 39.96. Result ID: 6992a6043a6c314849106387.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72f91e209131cea59aca.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72f91e209131cea59aca.md>)

[Implementation](<https://github.com/inQbator-eviCore/LLM_section_identifiers>)

Recorded evaluation configuration: {"Prompting Strategy":"Close Ended Prompt"}. This record does not assert independent reproduction.

### LLaMa-2

Accuracy: 38.21. Result ID: 6992a6043a6c31484910638a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72f91e209131cea59aca.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72f91e209131cea59aca.md>)

[Implementation](<https://github.com/inQbator-eviCore/LLM_section_identifiers>)

Recorded evaluation configuration: {"Prompting Strategy":"Chain-of-Thought (CoT)"}. This record does not assert independent reproduction.

### Keyword Based

Accuracy: 36.07. Result ID: 6992a6043a6c314849106380.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72f91e209131cea59aca.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### LLaMa-2

Accuracy: 13.95. Result ID: 6992a6043a6c314849106389.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72f91e209131cea59aca.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72f91e209131cea59aca.md>)

[Implementation](<https://github.com/inQbator-eviCore/LLM_section_identifiers>)

Recorded evaluation configuration: {"Prompting Strategy":"One Shot Prompt"}. This record does not assert independent reproduction.

### Mistral

Accuracy: 11.99. Result ID: 6992a6043a6c31484910638e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72f91e209131cea59aca.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72f91e209131cea59aca.md>)

[Implementation](<https://github.com/inQbator-eviCore/LLM_section_identifiers>)

Recorded evaluation configuration: {"Prompting Strategy":"Chain-of-Thought (CoT)"}. This record does not assert independent reproduction.

### Mistral

Accuracy: 11.51. Result ID: 6992a6043a6c31484910638c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72f91e209131cea59aca.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72f91e209131cea59aca.md>)

[Implementation](<https://github.com/inQbator-eviCore/LLM_section_identifiers>)

Recorded evaluation configuration: {"Prompting Strategy":"Zero Shot Prompt"}. This record does not assert independent reproduction.

### Mistral

Accuracy: 8.41. Result ID: 6992a6043a6c31484910638d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72f91e209131cea59aca.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72f91e209131cea59aca.md>)

[Implementation](<https://github.com/inQbator-eviCore/LLM_section_identifiers>)

Recorded evaluation configuration: {"Prompting Strategy":"One Shot Prompt"}. This record does not assert independent reproduction.

### Mistral

Accuracy: 5.24. Result ID: 6992a6043a6c31484910638b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72f91e209131cea59aca.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72f91e209131cea59aca.md>)

[Implementation](<https://github.com/inQbator-eviCore/LLM_section_identifiers>)

Recorded evaluation configuration: {"Prompting Strategy":"Close Ended Prompt"}. This record does not assert independent reproduction.

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