# Multi-hop Knowledge-based Question Answering on PathQuestion (PQ) 3H 1.0

Source: [Multi-hop Knowledge-based Question Answering on PathQuestion (PQ) 3H 1.0](<https://www.sota2.com/research/sota/multi-hop-knowledge-based-question-answering-on-pathquestion-pq-3h-1-0>)

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

Data updated: 2026-02-26T05:28:15.380Z

Evaluation of model performance on the PathQuestion (PQ) 3H 1.0 dataset for Multi-hop Knowledge-based Question Answering, measured using 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 | Multi-hop Knowledge-based Question Answering |
| Dataset (including any stated split) | PathQuestion (PQ) 3H 1.0 |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 10 of 10 |
| 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/multi-hop-knowledge-based-question-answering-on-pathquestion-pq-3h-1-0.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Hypergraph Transformer | 90.3 | Not recorded | 68fa6c571e209131cea3367d |
| SRN | 89.2 | Not recorded | 68fa6c571e209131cea3367d |
| IRN | 87.7 | Not recorded | 68fa6c571e209131cea3367d |
| IRN-weak | 83.3 | Not recorded | 68fa6c571e209131cea3367d |
| KV-MemNN | 79.4 | Not recorded | 68fa6c571e209131cea3367d |
| MemNN | 79.2 | Not recorded | 68fa6c571e209131cea3367d |
| Seq2Seq | 77 | Not recorded | 68fa6c571e209131cea3367d |
| MINERVA | 71.2 | Not recorded | 68fa6c571e209131cea3367d |
| Subgraph | 50.6 | Not recorded | 68fa6c571e209131cea3367d |
| Embed | 48.3 | Not recorded | 68fa6c571e209131cea3367d |

### Hypergraph Transformer

Accuracy: 90.3. Result ID: 698f05633a6c314849f4d849.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c571e209131cea3367d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c571e209131cea3367d.md>)

[Implementation](<https://github.com/yujungheo/kbvqa-public>)

Recorded evaluation configuration: {"Supervision":"Weakly-supervised"}. This record does not assert independent reproduction.

### SRN

Accuracy: 89.2. Result ID: 698f05633a6c314849f4d848.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c571e209131cea3367d.md>)

Recorded evaluation configuration: {"Supervision":"Weakly-supervised"}. This record does not assert independent reproduction.

### IRN

Accuracy: 87.7. Result ID: 698f05633a6c314849f4d843.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c571e209131cea3367d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa646c1e209131cea049d4.md>)

Recorded evaluation configuration: {"Supervision":"Fully-supervised"}. This record does not assert independent reproduction.

### IRN-weak

Accuracy: 83.3. Result ID: 698f05633a6c314849f4d847.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c571e209131cea3367d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa646c1e209131cea049d4.md>)

Recorded evaluation configuration: {"Supervision":"Weakly-supervised"}. This record does not assert independent reproduction.

### KV-MemNN

Accuracy: 79.4. Result ID: 698f05633a6c314849f4d842.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c571e209131cea3367d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62d51e209131ce9fb76c.md>)

Recorded evaluation configuration: {"Supervision":"Fully-supervised"}. This record does not assert independent reproduction.

### MemNN

Accuracy: 79.2. Result ID: 698f05633a6c314849f4d841.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c571e209131cea3367d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa622f1e209131ce9f80a6.md>)

[Implementation](<https://github.com/facebook/MemNN>)

Recorded evaluation configuration: {"Supervision":"Fully-supervised"}. This record does not assert independent reproduction.

### Seq2Seq

Accuracy: 77. Result ID: 698f05633a6c314849f4d840.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c571e209131cea3367d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa619e1e209131ce9f5369.md>)

Recorded evaluation configuration: {"Supervision":"Fully-supervised"}. This record does not assert independent reproduction.

### MINERVA

Accuracy: 71.2. Result ID: 698f05633a6c314849f4d846.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c571e209131cea3367d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65391e209131cea09235.md>)

Recorded evaluation configuration: {"Supervision":"Weakly-supervised"}. This record does not assert independent reproduction.

### Subgraph

Accuracy: 50.6. Result ID: 698f05633a6c314849f4d845.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c571e209131cea3367d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa617c1e209131ce9f4664.md>)

Recorded evaluation configuration: {"Supervision":"Weakly-supervised"}. This record does not assert independent reproduction.

### Embed

Accuracy: 48.3. Result ID: 698f05633a6c314849f4d844.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c571e209131cea3367d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa61501e209131ce9f3bdf.md>)

Recorded evaluation configuration: {"Supervision":"Weakly-supervised"}. This record does not assert independent reproduction.

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