# Open-Domain Conversational Question Answering on TopiOCQA (val)

Source: [Open-Domain Conversational Question Answering on TopiOCQA (val)](<https://www.sota2.com/research/sota/open-domain-conversational-question-answering-on-topiocqa-val>)

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

Data updated: 2026-02-26T05:42:45.769Z

Evaluation of model performance on the validation split of the TopiOCQA dataset for Open-Domain Conversational Question Answering, typically measured using 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 | Open-Domain Conversational Question Answering |
| Dataset (including any stated split) | TopiOCQA (val) |
| Metric | F1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [F1](<https://www.sota2.com/research/sota/open-domain-conversational-question-answering-on-topiocqa-val.md?metric=F1>): Higher is better; unit: PERCENT.

- [EM](<https://www.sota2.com/research/sota/open-domain-conversational-question-answering-on-topiocqa-val.md?metric=EM>): Higher is better; unit: PERCENT.

## Recorded results

| Method | F1 | Result date | Report paper |
| --- | --- | --- | --- |
| PRO-ConvQA | 36.67 | Not recorded | 68fa6f9d1e209131cea469cb |
| DPR Ret. + DPR Read. | 23.13 | Not recorded | 68fa6f9d1e209131cea469cb |
| BM25 Ret. + DPR Read. | 13.92 | Not recorded | 68fa6f9d1e209131cea469cb |
| ORConvQA | 10.67 | Not recorded | 68fa6f9d1e209131cea469cb |

### PRO-ConvQA

F1: 36.67. Result ID: 6990f5b23a6c3148490499fc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f9d1e209131cea469cb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f9d1e209131cea469cb.md>)

[Implementation](<https://github.com/starsuzi/PRO-ConvQA>)

Recorded evaluation configuration: {"Mechanism":"Directly retrieves answers without passage reading","Training":"Jointly with contrastive learning"}. This record does not assert independent reproduction.

### DPR Ret. + DPR Read.

F1: 23.13. Result ID: 6990f5b23a6c3148490499fa.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f9d1e209131cea469cb.md>)

Recorded evaluation configuration: {"Retriever":"DPR (Dense)","Reader":"DPR Reader"}. This record does not assert independent reproduction.

### BM25 Ret. + DPR Read.

F1: 13.92. Result ID: 6990f5b23a6c3148490499f9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f9d1e209131cea469cb.md>)

Recorded evaluation configuration: {"Retriever":"BM25 (Sparse)","Reader":"DPR Reader"}. This record does not assert independent reproduction.

### ORConvQA

F1: 10.67. Result ID: 6990f5b23a6c3148490499fb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f9d1e209131cea469cb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67991e209131cea175a1.md>)

Recorded evaluation configuration: {"Architecture":"Dense retriever, reader, and additional re-ranker"}. This record does not assert independent reproduction.

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