# Open-set knowledge retrieval on Google RE (UHN)

Source: [Open-set knowledge retrieval on Google RE (UHN)](<https://www.sota2.com/research/sota/open-set-knowledge-retrieval-on-google-re-uhn>)

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

Data updated: 2026-02-27T08:17:50.014Z

Evaluation of model performance on open-set knowledge retrieval using the Google RE dataset, specifically the UHN split, measured by Macro-averaged 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 | Open-set knowledge retrieval |
| Dataset (including any stated split) | Google RE (UHN) |
| Metric | Macro EM |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 19 of 19 |
| 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

- [Macro EM](<https://www.sota2.com/research/sota/open-set-knowledge-retrieval-on-google-re-uhn.md?metric=Macro%20EM>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Macro EM | Result date | Report paper |
| --- | --- | --- | --- |
| NPM | 23 | Not recorded | 68fa6f7f1e209131cea45f9d |
| BM25 + T5 | 16.6 | Not recorded | 68fa6f7f1e209131cea45f9d |
| BM25 + T5 3B | 15.5 | Not recorded | 68fa6f7f1e209131cea45f9d |
| BM25 + GPT-3 175B | 11.9 | Not recorded | 68fa6f7f1e209131cea45f9d |
| BM25 + GPT-3 13B | 11.2 | Not recorded | 68fa6f7f1e209131cea45f9d |
| BM25 + OPT 2.7B | 3.7 | Not recorded | 68fa6f7f1e209131cea45f9d |
| BM25 + GPT-3 6.7B | 3.5 | Not recorded | 68fa6f7f1e209131cea45f9d |
| BM25 + OPT 6.7B | 3.3 | Not recorded | 68fa6f7f1e209131cea45f9d |
| BM25 + OPT 13B | 3.1 | Not recorded | 68fa6f7f1e209131cea45f9d |
| GPT-3 175B | 1 | Not recorded | 68fa6f7f1e209131cea45f9d |
| T5 3B | 0.7 | Not recorded | 68fa6f7f1e209131cea45f9d |
| T5 | 0.4 | Not recorded | 68fa6f7f1e209131cea45f9d |
| GPT-3 13B | 0.4 | Not recorded | 68fa6f7f1e209131cea45f9d |
| OPT 6.7B | 0.3 | Not recorded | 68fa6f7f1e209131cea45f9d |
| OPT 13B | 0.3 | Not recorded | 68fa6f7f1e209131cea45f9d |
| BM25 + GPT-3 2.7B | 0.1 | Not recorded | 68fa6f7f1e209131cea45f9d |
| OPT 2.7B | 0 | Not recorded | 68fa6f7f1e209131cea45f9d |
| GPT-3 2.7B | 0 | Not recorded | 68fa6f7f1e209131cea45f9d |
| GPT-3 6.7B | 0 | Not recorded | 68fa6f7f1e209131cea45f9d |

### NPM

Macro EM: 23. Result ID: 69a1531a35dfcabb00e64621.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45f9d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45f9d.md>)

[Implementation](<https://www.sota2.com/github.com/facebookresearch/NPM>)

Recorded evaluation configuration: {"#Params":"1.0x","C (Text Corpus)":"true","Zero-shot":"true"}. This record does not assert independent reproduction.

### BM25 + T5

Macro EM: 16.6. Result ID: 69a1531a35dfcabb00e64611.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45f9d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa709e1e209131cea4c470.md>)

[Implementation](<https://github.com/google-research/text-to-text-transfer-transformer>)

Recorded evaluation configuration: {"#Params":"2.2x","C (Text Corpus)":"true","Zero-shot":"true"}. This record does not assert independent reproduction.

### BM25 + T5 3B

Macro EM: 15.5. Result ID: 69a1531a35dfcabb00e64612.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45f9d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa709e1e209131cea4c470.md>)

[Implementation](<https://github.com/google-research/text-to-text-transfer-transformer>)

Recorded evaluation configuration: {"#Params":"8.5x","C (Text Corpus)":"true","Zero-shot":"true"}. This record does not assert independent reproduction.

### BM25 + GPT-3 175B

Macro EM: 11.9. Result ID: 69a1531a35dfcabb00e64620.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45f9d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa680c1e209131cea19d53.md>)

[Implementation](<https://github.com/openai/gpt-3/blob/master/overlap_frequency.md>)

Recorded evaluation configuration: {"#Params":"500x","C (Text Corpus)":"true","Zero-shot":"true"}. This record does not assert independent reproduction.

### BM25 + GPT-3 13B

Macro EM: 11.2. Result ID: 69a1531a35dfcabb00e6461f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45f9d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa680c1e209131cea19d53.md>)

[Implementation](<https://github.com/openai/gpt-3/blob/master/overlap_frequency.md>)

Recorded evaluation configuration: {"#Params":"37x","C (Text Corpus)":"true","Zero-shot":"true"}. This record does not assert independent reproduction.

### BM25 + OPT 2.7B

Macro EM: 3.7. Result ID: 69a1531a35dfcabb00e6461a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45f9d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cda1e209131cea36474.md>)

[Implementation](<https://github.com/facebookresearch/metaseq>)

Recorded evaluation configuration: {"#Params":"7.6x","C (Text Corpus)":"true","Zero-shot":"true"}. This record does not assert independent reproduction.

### BM25 + GPT-3 6.7B

Macro EM: 3.5. Result ID: 69a1531a35dfcabb00e6461d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45f9d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa680c1e209131cea19d53.md>)

[Implementation](<https://github.com/openai/gpt-3/blob/master/overlap_frequency.md>)

Recorded evaluation configuration: {"#Params":"19x","C (Text Corpus)":"true","Zero-shot":"true"}. This record does not assert independent reproduction.

### BM25 + OPT 6.7B

Macro EM: 3.3. Result ID: 69a1531a35dfcabb00e6461c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45f9d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cda1e209131cea36474.md>)

[Implementation](<https://github.com/facebookresearch/metaseq>)

Recorded evaluation configuration: {"#Params":"19x","C (Text Corpus)":"true","Zero-shot":"true"}. This record does not assert independent reproduction.

### BM25 + OPT 13B

Macro EM: 3.1. Result ID: 69a1531a35dfcabb00e6461e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45f9d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cda1e209131cea36474.md>)

[Implementation](<https://github.com/facebookresearch/metaseq>)

Recorded evaluation configuration: {"#Params":"37x","C (Text Corpus)":"true","Zero-shot":"true"}. This record does not assert independent reproduction.

### GPT-3 175B

Macro EM: 1. Result ID: 69a1531a35dfcabb00e64619.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45f9d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a201e209131cea261f0.md>)

Recorded evaluation configuration: {"#Params":"500x","C (Text Corpus)":"false","Zero-shot":"true"}. This record does not assert independent reproduction.

### T5 3B

Macro EM: 0.7. Result ID: 69a1531a35dfcabb00e64610.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45f9d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa709e1e209131cea4c470.md>)

[Implementation](<https://github.com/google-research/text-to-text-transfer-transformer>)

Recorded evaluation configuration: {"#Params":"8.5x","C (Text Corpus)":"false","Zero-shot":"true"}. This record does not assert independent reproduction.

### T5

Macro EM: 0.4. Result ID: 69a1531a35dfcabb00e6460f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45f9d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa709e1e209131cea4c470.md>)

[Implementation](<https://github.com/google-research/text-to-text-transfer-transformer>)

Recorded evaluation configuration: {"#Params":"2.2x","C (Text Corpus)":"false","Zero-shot":"true"}. This record does not assert independent reproduction.

### GPT-3 13B

Macro EM: 0.4. Result ID: 69a1531a35dfcabb00e64618.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45f9d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e031e209131cea3d6a3.md>)

Recorded evaluation configuration: {"#Params":"37x","C (Text Corpus)":"false","Zero-shot":"true"}. This record does not assert independent reproduction.

### OPT 6.7B

Macro EM: 0.3. Result ID: 69a1531a35dfcabb00e64615.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45f9d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cda1e209131cea36474.md>)

[Implementation](<https://github.com/facebookresearch/metaseq>)

Recorded evaluation configuration: {"#Params":"19x","C (Text Corpus)":"false","Zero-shot":"true"}. This record does not assert independent reproduction.

### OPT 13B

Macro EM: 0.3. Result ID: 69a1531a35dfcabb00e64617.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45f9d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cda1e209131cea36474.md>)

[Implementation](<https://github.com/facebookresearch/metaseq>)

Recorded evaluation configuration: {"#Params":"37x","C (Text Corpus)":"false","Zero-shot":"true"}. This record does not assert independent reproduction.

### BM25 + GPT-3 2.7B

Macro EM: 0.1. Result ID: 69a1531a35dfcabb00e6461b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45f9d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa680c1e209131cea19d53.md>)

[Implementation](<https://github.com/openai/gpt-3/blob/master/overlap_frequency.md>)

Recorded evaluation configuration: {"#Params":"7.6x","C (Text Corpus)":"true","Zero-shot":"true"}. This record does not assert independent reproduction.

### OPT 2.7B

Macro EM: 0. Result ID: 69a1531a35dfcabb00e64613.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45f9d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cda1e209131cea36474.md>)

[Implementation](<https://github.com/facebookresearch/metaseq>)

Recorded evaluation configuration: {"#Params":"7.6x","C (Text Corpus)":"false","Zero-shot":"true"}. This record does not assert independent reproduction.

### GPT-3 2.7B

Macro EM: 0. Result ID: 69a1531a35dfcabb00e64614.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45f9d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a201e209131cea261f0.md>)

Recorded evaluation configuration: {"#Params":"7.6x","C (Text Corpus)":"false","Zero-shot":"true"}. This record does not assert independent reproduction.

### GPT-3 6.7B

Macro EM: 0. Result ID: 69a1531a35dfcabb00e64616.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45f9d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e031e209131cea3d6a3.md>)

Recorded evaluation configuration: {"#Params":"19x","C (Text Corpus)":"false","Zero-shot":"true"}. This record does not assert independent reproduction.

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