# Citation Quality Assessment on BioACE N = 50 runs 2025

Source: [Citation Quality Assessment on BioACE N = 50 runs 2025](<https://www.sota2.com/research/sota/citation-quality-assessment-on-bioace-n-50-runs-2025>)

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

Data updated: 2026-03-19T09:36:23.439Z

Evaluation of model performance on the BioACE dataset (N=50 runs, 2025 evaluation set) for Citation Quality Assessment, measured by Citation Coverage, Support Rate, and Contradict Rate.

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 | Citation Quality Assessment |
| Dataset (including any stated split) | BioACE N = 50 runs 2025 |
| Metric | Citation Coverage |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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

- [Citation Coverage](<https://www.sota2.com/research/sota/citation-quality-assessment-on-bioace-n-50-runs-2025.md?metric=Citation%20Coverage>): Higher is better; unit: PERCENT.

- [Citation Support Rate](<https://www.sota2.com/research/sota/citation-quality-assessment-on-bioace-n-50-runs-2025.md?metric=Citation%20Support%20Rate>): Higher is better; unit: PERCENT.

- [Citation Contradict Rate](<https://www.sota2.com/research/sota/citation-quality-assessment-on-bioace-n-50-runs-2025.md?metric=Citation%20Contradict%20Rate>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Citation Coverage | Result date | Report paper |
| --- | --- | --- | --- |
| dal | 99.36 | Not recorded | 69bb83260636e5bf4afc1bc1 |
| dal | 99.3 | Not recorded | 69bb83260636e5bf4afc1bc1 |
| GEHC-HTIC | 98.77 | Not recorded | 69bb83260636e5bf4afc1bc1 |
| h2oloo | 98.59 | Not recorded | 69bb83260636e5bf4afc1bc1 |
| SIB | 98.21 | Not recorded | 69bb83260636e5bf4afc1bc1 |
| hltbio | 96.97 | Not recorded | 69bb83260636e5bf4afc1bc1 |
| hltbio | 96.95 | Not recorded | 69bb83260636e5bf4afc1bc1 |
| Track Mean | 80.23 | Not recorded | 69bb83260636e5bf4afc1bc1 |
| Baseline | 55.76 | Not recorded | 69bb83260636e5bf4afc1bc1 |

### dal

Citation Coverage: 99.36. Result ID: 69bbc39147f34ce924a604b3.

[Reporting paper](<https://www.sota2.com/research/paper/69bb83260636e5bf4afc1bc1.md>)

Recorded evaluation configuration: {"Run (abbreviated)":"rrf\_llama70b"}. This record does not assert independent reproduction.

### dal

Citation Coverage: 99.3. Result ID: 69bbc39147f34ce924a604b4.

[Reporting paper](<https://www.sota2.com/research/paper/69bb83260636e5bf4afc1bc1.md>)

Recorded evaluation configuration: {"Run (abbreviated)":"rrf\_llama70b\_no-val"}. This record does not assert independent reproduction.

### GEHC-HTIC

Citation Coverage: 98.77. Result ID: 69bbc39147f34ce924a604b5.

[Reporting paper](<https://www.sota2.com/research/paper/69bb83260636e5bf4afc1bc1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69bb83260636e5bf4afc1bc1.md>)

Recorded evaluation configuration: {"Run (abbreviated)":"pubmedbert\_medcpt\_gpt4o"}. This record does not assert independent reproduction.

### h2oloo

Citation Coverage: 98.59. Result ID: 69bbc39147f34ce924a604b6.

[Reporting paper](<https://www.sota2.com/research/paper/69bb83260636e5bf4afc1bc1.md>)

Recorded evaluation configuration: {"Run (abbreviated)":"h2oloo\_rr\_g41\_t50"}. This record does not assert independent reproduction.

### SIB

Citation Coverage: 98.21. Result ID: 69bbc39147f34ce924a604b7.

[Reporting paper](<https://www.sota2.com/research/paper/69bb83260636e5bf4afc1bc1.md>)

Recorded evaluation configuration: {"Run (abbreviated)":"SIB-task-b-3"}. This record does not assert independent reproduction.

### hltbio

Citation Coverage: 96.97. Result ID: 69bbc39147f34ce924a604b8.

[Reporting paper](<https://www.sota2.com/research/paper/69bb83260636e5bf4afc1bc1.md>)

Recorded evaluation configuration: {"Run (abbreviated)":"hltbio-gpt5.searcher"}. This record does not assert independent reproduction.

### hltbio

Citation Coverage: 96.95. Result ID: 69bbc39147f34ce924a604b9.

[Reporting paper](<https://www.sota2.com/research/paper/69bb83260636e5bf4afc1bc1.md>)

Recorded evaluation configuration: {"Run (abbreviated)":"hltbio-lg.listllama"}. This record does not assert independent reproduction.

### Track Mean

Citation Coverage: 80.23. Result ID: 69bbc39147f34ce924a604ba.

[Reporting paper](<https://www.sota2.com/research/paper/69bb83260636e5bf4afc1bc1.md>)

Recorded evaluation configuration: {"n":"50"}. This record does not assert independent reproduction.

### Baseline

Citation Coverage: 55.76. Result ID: 69bbc39147f34ce924a604bb.

[Reporting paper](<https://www.sota2.com/research/paper/69bb83260636e5bf4afc1bc1.md>)

Recorded evaluation configuration: {"Run (abbreviated)":"task\_b\_baseline"}. This record does not assert independent reproduction.

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