# Discourse Question Answering on NarrativeQA (F1 score) Source: [Discourse Question Answering on NarrativeQA (F1 score)]() Collection index: [llms.txt]() Data updated: 2026-06-30T06:32:43.940Z Evaluation of Discourse Question Answering performance on the NarrativeQA dataset, reporting the F1 score. 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 | Discourse Question Answering | | Dataset (including any stated split) | NarrativeQA | | Metric | F1 Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 14 of 14 | | 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 Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | F1 Score | Result date | Report paper | | --- | --- | --- | --- | | SemFlowRAG | 26.6 | Not recorded | 6a434d72ba73165dbb74383b | | HippoRAG 2 (reproduced) | 26.2 | Not recorded | 6a434d72ba73165dbb74383b | | HippoRAG 2 | 25.9 | Not recorded | 6a434d72ba73165dbb74383b | | NV-Embed-v2 (7B) | 25.7 | Not recorded | 6a434d72ba73165dbb74383b | | GritLM-7B | 23.9 | Not recorded | 6a434d72ba73165dbb74383b | | GraphRAG | 23 | Not recorded | 6a434d72ba73165dbb74383b | | RAPTOR | 21.4 | Not recorded | 6a434d72ba73165dbb74383b | | GTE-Qwen2-7B-Instruct | 21.3 | Not recorded | 6a434d72ba73165dbb74383b | | GTR | 19.9 | Not recorded | 6a434d72ba73165dbb74383b | | Contriever | 19.7 | Not recorded | 6a434d72ba73165dbb74383b | | BM25 | 18.3 | Not recorded | 6a434d72ba73165dbb74383b | | HippoRAG | 16.3 | Not recorded | 6a434d72ba73165dbb74383b | | Llama-3.3-70B-Instruct w/o Retrieval | 12.9 | Not recorded | 6a434d72ba73165dbb74383b | | LightRAG | 3.7 | Not recorded | 6a434d72ba73165dbb74383b | ### SemFlowRAG F1 Score: 26.6. Result ID: 6a4362f0fbc373592c92a42a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Knowledge Representation":"Structured"}. This record does not assert independent reproduction. ### HippoRAG 2 (reproduced) F1 Score: 26.2. Result ID: 6a4362f0fbc373592c92a429. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Knowledge Representation":"Structured","Reproduction Status":"reproduced"}. This record does not assert independent reproduction. ### HippoRAG 2 F1 Score: 25.9. Result ID: 6a4362f0fbc373592c92a428. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Knowledge Representation":"Structured"}. This record does not assert independent reproduction. ### NV-Embed-v2 (7B) F1 Score: 25.7. Result ID: 6a4362f0fbc373592c92a423. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Knowledge Representation":"Embedding-based"}. This record does not assert independent reproduction. ### GritLM-7B F1 Score: 23.9. Result ID: 6a4362f0fbc373592c92a422. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Knowledge Representation":"Embedding-based"}. This record does not assert independent reproduction. ### GraphRAG F1 Score: 23. Result ID: 6a4362f0fbc373592c92a425. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Knowledge Representation":"Structured"}. This record does not assert independent reproduction. ### RAPTOR F1 Score: 21.4. Result ID: 6a4362f0fbc373592c92a424. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Knowledge Representation":"Structured"}. This record does not assert independent reproduction. ### GTE-Qwen2-7B-Instruct F1 Score: 21.3. Result ID: 6a4362f0fbc373592c92a421. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Knowledge Representation":"Embedding-based"}. This record does not assert independent reproduction. ### GTR F1 Score: 19.9. Result ID: 6a4362f0fbc373592c92a420. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Knowledge Representation":"Unstructured"}. This record does not assert independent reproduction. ### Contriever F1 Score: 19.7. Result ID: 6a4362f0fbc373592c92a41f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Knowledge Representation":"Unstructured"}. This record does not assert independent reproduction. ### BM25 F1 Score: 18.3. Result ID: 6a4362f0fbc373592c92a41e. [Reporting paper]() Recorded evaluation configuration: {"Knowledge Representation":"Unstructured"}. This record does not assert independent reproduction. ### HippoRAG F1 Score: 16.3. Result ID: 6a4362f0fbc373592c92a427. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Knowledge Representation":"Structured"}. This record does not assert independent reproduction. ### Llama-3.3-70B-Instruct w/o Retrieval F1 Score: 12.9. Result ID: 6a4362f0fbc373592c92a41d. [Reporting paper]() Recorded evaluation configuration: {"Knowledge Representation":"Unstructured","Retrieval":"w/o Retrieval"}. This record does not assert independent reproduction. ### LightRAG F1 Score: 3.7. Result ID: 6a4362f0fbc373592c92a426. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Knowledge Representation":"Structured"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.