# Multi-hop Question Answering on Legal Source: [Multi-hop Question Answering on Legal]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:43:46.312Z Evaluation of model performance on the Legal dataset for Multi-hop Question Answering tasks, measured using F1, R-S, and G-E scores. 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 Question Answering | | Dataset (including any stated split) | Legal | | 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. - [R-S Score](): Higher is better; unit: PERCENT. - [G-E Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | F1 Score | Result date | Report paper | | --- | --- | --- | --- | | PRoH | 71.93 | Not recorded | 68fa7c1b1e209131cea8c606 | | PRoH-L | 60.25 | Not recorded | 68fa7c1b1e209131cea8c606 | | PRoH | 58.81 | Not recorded | 68fa7c1b1e209131cea8c606 | | PRoH-L | 51.4 | Not recorded | 68fa7c1b1e209131cea8c606 | | HyperGraphRAG | 43.81 | Not recorded | 68fa7c1b1e209131cea8c606 | | COT | 43.36 | Not recorded | 68fa7c1b1e209131cea8c606 | | IO | 43.2 | Not recorded | 68fa7c1b1e209131cea8c606 | | SC | 40.59 | Not recorded | 68fa7c1b1e209131cea8c606 | | HyperGraphRAG | 38.45 | Not recorded | 68fa7c1b1e209131cea8c606 | | StandardRAG | 37.34 | Not recorded | 68fa7c1b1e209131cea8c606 | | StandardRAG | 35.86 | Not recorded | 68fa7c1b1e209131cea8c606 | | PathRAG | 31.29 | Not recorded | 68fa7c1b1e209131cea8c606 | | LLM-only | 21.64 | Not recorded | 68fa7c1b1e209131cea8c606 | | HippoRAG2 | 18.53 | Not recorded | 68fa7c1b1e209131cea8c606 | ### PRoH F1 Score: 71.93. Result ID: 699ae5805698665ec475afae. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"variant":"Full"}. This record does not assert independent reproduction. ### PRoH-L F1 Score: 60.25. Result ID: 699ae5805698665ec475afad. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"variant":"Lightweight"}. This record does not assert independent reproduction. ### PRoH F1 Score: 58.81. Result ID: 699ae5805698665ec475afd1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### PRoH-L F1 Score: 51.4. Result ID: 699ae5805698665ec475afd0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"variant":"Light"}. This record does not assert independent reproduction. ### HyperGraphRAG F1 Score: 43.81. Result ID: 699ae5805698665ec475afcf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### COT F1 Score: 43.36. Result ID: 699ae5805698665ec475afa9. [Reporting paper]() Recorded evaluation configuration: {"mode":"LLM-only"}. This record does not assert independent reproduction. ### IO F1 Score: 43.2. Result ID: 699ae5805698665ec475afa8. [Reporting paper]() Recorded evaluation configuration: {"mode":"LLM-only"}. This record does not assert independent reproduction. ### SC F1 Score: 40.59. Result ID: 699ae5805698665ec475afaa. [Reporting paper]() Recorded evaluation configuration: {"mode":"LLM-only"}. This record does not assert independent reproduction. ### HyperGraphRAG F1 Score: 38.45. Result ID: 699ae5805698665ec475afac. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### StandardRAG F1 Score: 37.34. Result ID: 699ae5805698665ec475afcc. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### StandardRAG F1 Score: 35.86. Result ID: 699ae5805698665ec475afab. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### PathRAG F1 Score: 31.29. Result ID: 699ae5805698665ec475afcd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### LLM-only F1 Score: 21.64. Result ID: 699ae5805698665ec475afcb. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### HippoRAG2 F1 Score: 18.53. Result ID: 699ae5805698665ec475afce. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.